upd

app_inference.py

@@ -1,6 +1,5 @@
 from PytorchBoot.application import PytorchBootApplication
 from runners.inferencer import Inferencer
-from runners.inference_server import InferencerServer
 
 @PytorchBootApplication("inference")
 class InferenceApp:
@@ -15,17 +14,3 @@ class InferenceApp:
                 Evaluator("path_to_your_eval_config").run()
         '''       
         Inferencer("./configs/local/inference_config.yaml").run()
-
-@PytorchBootApplication("server")
-class InferenceServerApp:
-    @staticmethod
-    def start():
-        ''' 
-            call default or your custom runners here, code will be executed 
-        automatically when type "pytorch-boot run" or "ptb run" in terminal
-        
-            example:
-                Trainer("path_to_your_train_config").run()
-                Evaluator("path_to_your_eval_config").run()
-        '''       
-        InferencerServer("./configs/server/server_inference_server_config.yaml").run()

configs/local/inference_config.yaml

@@ -1,72 +1,76 @@
 
 runner:
   general:
-    seed: 0
+    seed: 1
     device: cuda
     cuda_visible_devices: "0,1,2,3,4,5,6,7"
     
   experiment:
-    name: train_ab_global_only
+    name: w_gf_wo_lf_full
     root_dir: "experiments"
-    epoch: -1 # -1 stands for last epoch
+    epoch: 1 # -1 stands for last epoch
 
   test:
     dataset_list:
-      - OmniObject3d_test
+      - OmniObject3d_train
 
   blender_script_path: "/media/hofee/data/project/python/nbv_reconstruction/blender/data_renderer.py"
-  output_dir: "/media/hofee/data/data/new_inference_test_output"
+  output_dir: "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/test/inference_global_full_on_testset"
-  pipeline: nbv_reconstruction_pipeline
+  pipeline: nbv_reconstruction_global_pts_pipeline
-  voxel_size: 0.003
   
 dataset:
-  # OmniObject3d_train:
+  OmniObject3d_train:
-  #   root_dir: "C:\\Document\\Datasets\\inference_test1"
+    root_dir: "/media/hofee/repository/nbv_reconstruction_data_512"
-  #   model_dir: "C:\\Document\\Datasets\\scaled_object_meshes"
-  #   source: seq_reconstruction_dataset_preprocessed
-  #   split_file: "C:\\Document\\Datasets\\data_list\\sample.txt"
-  #   type: test
-  #   filter_degree: 75
-  #   ratio: 1
-  #   batch_size: 1
-  #   num_workers: 12
-  #   pts_num: 8192
-  #   load_from_preprocess: True
-
-  OmniObject3d_test:
-    root_dir: "/media/hofee/data/data/new_testset_output"
     model_dir: "/media/hofee/data/data/scaled_object_meshes"
-    source: seq_reconstruction_dataset_preprocessed
+    source: seq_nbv_reconstruction_dataset
-    # split_file: "C:\\Document\\Datasets\\data_list\\OmniObject3d_test.txt"
+    split_file: "/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/test/test_set_list.txt"
     type: test
     filter_degree: 75
-    eval_list:
+    ratio: 1
-      - pose_diff
-      - coverage_rate_increase
-    ratio: 0.1
     batch_size: 1
     num_workers: 12
-    pts_num: 8192
+    pts_num: 4096
-    load_from_preprocess: True
+    load_from_preprocess: False
 
 pipeline:
-  nbv_reconstruction_pipeline:
+  nbv_reconstruction_local_pts_pipeline:
     modules:
       pts_encoder: pointnet_encoder
       seq_encoder: transformer_seq_encoder
       pose_encoder: pose_encoder
       view_finder: gf_view_finder
     eps: 1e-5
+    global_scanned_feat: False
+
+  nbv_reconstruction_global_pts_pipeline:
+    modules:
+      pts_encoder: pointnet_encoder
+      pose_seq_encoder: transformer_pose_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: gf_view_finder
+    eps: 1e-5
     global_scanned_feat: True
 
+
+    
 module:
+
   pointnet_encoder:
     in_dim: 3
     out_dim: 1024
     global_feat: True
     feature_transform: False
+
   transformer_seq_encoder:
-    embed_dim: 256
+    pts_embed_dim: 1024
+    pose_embed_dim: 256
+    num_heads: 4
+    ffn_dim: 256
+    num_layers: 3
+    output_dim: 2048
+
+  transformer_pose_seq_encoder:
+    pose_embed_dim: 256
     num_heads: 4
     ffn_dim: 256
     num_layers: 3
@@ -82,8 +86,7 @@ module:
     sample_mode: ode
     sampling_steps: 500
     sde_mode: ve
+
   pose_encoder:
     pose_dim: 9
     out_dim: 256
-  pts_num_encoder:
-    out_dim: 64

configs/local/view_generate_config.yaml

@@ -7,19 +7,17 @@ runner:
     name: debug
     root_dir: experiments
   generate:
-    port: 5000
+    port: 5002
-    from: 0
+    from: 600
     to: -1 # -1 means all
-    object_dir: /media/hofee/data/data/scaled_object_meshes
+    object_dir: /media/hofee/data/data/object_meshes_part1
     table_model_path: "/media/hofee/data/data/others/table.obj"
-    output_dir: /media/hofee/data/data/new_testset
+    output_dir: /media/hofee/repository/data_part_1
-    object_list_path: /media/hofee/data/data/OmniObject3d_test.txt
-    use_list: True
     binocular_vision: true
     plane_size: 10
     max_views: 512
     min_views: 128
-    random_view_ratio: 0.01
+    random_view_ratio: 0.02
     min_cam_table_included_degree: 20
     max_diag: 0.7
     min_diag: 0.01

configs/server/server_inference_server_config.yaml

@@ -1,53 +0,0 @@
-
-runner:
-  general:
-    seed: 0
-    device: cuda
-    cuda_visible_devices: "0,1,2,3,4,5,6,7"
-    
-  experiment:
-    name: train_ab_global_only
-    root_dir: "experiments"
-    epoch: -1 # -1 stands for last epoch
-
-  pipeline: nbv_reconstruction_pipeline
-  voxel_size: 0.003
-
-pipeline:
-  nbv_reconstruction_pipeline:
-    modules:
-      pts_encoder: pointnet_encoder
-      seq_encoder: transformer_seq_encoder
-      pose_encoder: pose_encoder
-      view_finder: gf_view_finder
-    eps: 1e-5
-    global_scanned_feat: True
-
-module:
-  pointnet_encoder:
-    in_dim: 3
-    out_dim: 1024
-    global_feat: True
-    feature_transform: False
-  transformer_seq_encoder:
-    embed_dim: 256
-    num_heads: 4
-    ffn_dim: 256
-    num_layers: 3
-    output_dim: 1024
-
-  gf_view_finder:
-    t_feat_dim: 128
-    pose_feat_dim: 256
-    main_feat_dim: 2048
-    regression_head: Rx_Ry_and_T
-    pose_mode: rot_matrix
-    per_point_feature: False
-    sample_mode: ode
-    sampling_steps: 500
-    sde_mode: ve
-  pose_encoder:
-    pose_dim: 9
-    out_dim: 256
-  pts_num_encoder:
-    out_dim: 64

configs/server/server_train_config.yaml

@@ -3,17 +3,17 @@ runner:
   general:
     seed: 0
     device: cuda
-    cuda_visible_devices: "0"
+    cuda_visible_devices: "1"
     parallel: False
     
   experiment:
-    name: train_ab_global_only
+    name: overfit_ab_local_only
     root_dir: "experiments"
-    use_checkpoint: True
+    use_checkpoint: False
     epoch: -1 # -1 stands for last epoch
     max_epochs: 5000
     save_checkpoint_interval: 1
-    test_first: True  
+    test_first: False  
 
   train:
     optimizer:
@@ -25,53 +25,53 @@ runner:
   test:
     frequency: 3 # test frequency
     dataset_list:
-      - OmniObject3d_test
+      #- OmniObject3d_test
       - OmniObject3d_val
 
   pipeline: nbv_reconstruction_pipeline
   
 dataset:
   OmniObject3d_train:
-    root_dir: "/data/hofee/data/new_full_data"
+    root_dir: "/data/hofee/nbv_rec_part2_preprocessed"
     model_dir: "../data/scaled_object_meshes"
     source: nbv_reconstruction_dataset
-    split_file: "/data/hofee/data/new_full_data_list/OmniObject3d_train.txt"
+    split_file: "/data/hofee/data/sample.txt"
     type: train
     cache: True
     ratio: 1
-    batch_size: 80
+    batch_size: 32
-    num_workers: 128
+    num_workers: 16
     pts_num: 8192
     load_from_preprocess: True
 
   OmniObject3d_test:
-    root_dir: "/data/hofee/data/new_full_data"
+    root_dir: "/data/hofee/nbv_rec_part2_preprocessed"
     model_dir: "../data/scaled_object_meshes"
     source: nbv_reconstruction_dataset
-    split_file: "/data/hofee/data/new_full_data_list/OmniObject3d_test.txt"
+    split_file: "/data/hofee/data/sample.txt"
     type: test
     cache: True
     filter_degree: 75
     eval_list:
       - pose_diff
     ratio: 1
-    batch_size: 80
+    batch_size: 32
     num_workers: 12
     pts_num: 8192
     load_from_preprocess: True
 
   OmniObject3d_val:
-    root_dir: "/data/hofee/data/new_full_data"
+    root_dir: "/data/hofee/nbv_rec_part2_preprocessed"
     model_dir: "../data/scaled_object_meshes"
     source: nbv_reconstruction_dataset
-    split_file: "/data/hofee/data/new_full_data_list/OmniObject3d_train.txt"
+    split_file: "/data/hofee/data/sample.txt"
     type: test
     cache: True
     filter_degree: 75
     eval_list:
       - pose_diff
-    ratio: 0.1
+    ratio: 1
-    batch_size: 80
+    batch_size: 32
     num_workers: 12
     pts_num: 8192
     load_from_preprocess: True
@@ -92,16 +92,16 @@ module:
 
   pointnet_encoder:
     in_dim: 3
-    out_dim: 1024
+    out_dim: 512
     global_feat: True
     feature_transform: False
 
   transformer_seq_encoder:
-    embed_dim: 256
+    embed_dim: 768
     num_heads: 4
     ffn_dim: 256
     num_layers: 3
-    output_dim: 1024
+    output_dim: 2048
 
   gf_view_finder:
     t_feat_dim: 128

core/nbv_dataset.py

@@ -34,7 +34,7 @@ class NBVReconstructionDataset(BaseDataset):
             #self.model_dir = config["model_dir"]
             self.filter_degree = config["filter_degree"]
         if self.type == namespace.Mode.TRAIN:
-            scale_ratio = 1
+            scale_ratio = 50
             self.datalist = self.datalist*scale_ratio
         if self.cache:
             expr_root = ConfigManager.get("runner", "experiment", "root_dir")
@@ -165,13 +165,8 @@ class NBVReconstructionDataset(BaseDataset):
             [best_to_world_6d, best_to_world_trans], axis=0
         )
 
-        combined_scanned_views_pts = np.concatenate(scanned_views_pts, axis=0)
-        voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_views_pts, 0.002)
-        random_downsampled_combined_scanned_pts_np = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, self.pts_num)
-        
         data_item = {
             "scanned_pts": np.asarray(scanned_views_pts, dtype=np.float32), # Ndarray(S x Nv x 3)
-            "combined_scanned_pts": np.asarray(random_downsampled_combined_scanned_pts_np, dtype=np.float32), # Ndarray(N x 3)
             "scanned_coverage_rate": scanned_coverages_rate, # List(S): Float, range(0, 1)
             "scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9)
             "best_coverage_rate": nbv_coverage_rate, # Float, range(0, 1)
@@ -203,15 +198,13 @@ class NBVReconstructionDataset(BaseDataset):
             collate_data["best_to_world_pose_9d"] = torch.stack(
                 [torch.tensor(item["best_to_world_pose_9d"]) for item in batch]
             )
-            collate_data["combined_scanned_pts"] = torch.stack(
+                
-                [torch.tensor(item["combined_scanned_pts"]) for item in batch]
-            )
             for key in batch[0].keys():
                 if key not in [
                     "scanned_pts",
+                    "scanned_pts_mask",
                     "scanned_n_to_world_pose_9d",
                     "best_to_world_pose_9d",
-                    "combined_scanned_pts",
                 ]:
                     collate_data[key] = [item[key] for item in batch]
             return collate_data

core/old_seq_dataset.py

@@ -1,154 +0,0 @@
-import numpy as np
-from PytorchBoot.dataset import BaseDataset
-import PytorchBoot.namespace as namespace
-import PytorchBoot.stereotype as stereotype
-from PytorchBoot.utils.log_util import Log
-import torch
-import os
-import sys
-sys.path.append(r"/home/data/hofee/project/nbv_rec/nbv_reconstruction")
-
-from utils.data_load import DataLoadUtil
-from utils.pose import PoseUtil
-from utils.pts import PtsUtil
-
-@stereotype.dataset("old_seq_nbv_reconstruction_dataset")
-class SeqNBVReconstructionDataset(BaseDataset):
-    def __init__(self, config):
-        super(SeqNBVReconstructionDataset, self).__init__(config)
-        self.type = config["type"]
-        if self.type != namespace.Mode.TEST:
-            Log.error("Dataset <seq_nbv_reconstruction_dataset> Only support test mode", terminate=True)
-        self.config = config
-        self.root_dir = config["root_dir"]
-        self.split_file_path = config["split_file"]
-        self.scene_name_list = self.load_scene_name_list()
-        self.datalist = self.get_datalist()
-        self.pts_num = config["pts_num"]
-        
-        self.model_dir = config["model_dir"]
-        self.filter_degree = config["filter_degree"]
-        self.load_from_preprocess = config.get("load_from_preprocess", False)
-        
-
-    def load_scene_name_list(self):
-        scene_name_list = []
-        with open(self.split_file_path, "r") as f:
-            for line in f:
-                scene_name = line.strip()
-                scene_name_list.append(scene_name)
-        return scene_name_list
-    
-    def get_datalist(self):
-        datalist = []
-        for scene_name in self.scene_name_list:
-            seq_num = DataLoadUtil.get_label_num(self.root_dir, scene_name)
-            scene_max_coverage_rate = 0
-            scene_max_cr_idx = 0
-
-            for seq_idx in range(seq_num):
-                label_path = DataLoadUtil.get_label_path(self.root_dir, scene_name, seq_idx)
-                label_data = DataLoadUtil.load_label(label_path)
-                max_coverage_rate = label_data["max_coverage_rate"]
-                if max_coverage_rate > scene_max_coverage_rate:
-                    scene_max_coverage_rate = max_coverage_rate
-                    scene_max_cr_idx = seq_idx
-        
-            label_path = DataLoadUtil.get_label_path(self.root_dir, scene_name, scene_max_cr_idx)
-            label_data = DataLoadUtil.load_label(label_path)
-            first_frame = label_data["best_sequence"][0]
-            best_seq_len = len(label_data["best_sequence"])
-            datalist.append({
-                    "scene_name": scene_name,
-                    "first_frame": first_frame,
-                    "max_coverage_rate": scene_max_coverage_rate,
-                    "best_seq_len": best_seq_len,
-                    "label_idx": scene_max_cr_idx,
-                })
-        return datalist
-
-    def __getitem__(self, index):
-        data_item_info = self.datalist[index]
-        first_frame_idx = data_item_info["first_frame"][0]
-        first_frame_coverage = data_item_info["first_frame"][1]
-        max_coverage_rate = data_item_info["max_coverage_rate"]
-        scene_name = data_item_info["scene_name"]
-        first_cam_info = DataLoadUtil.load_cam_info(DataLoadUtil.get_path(self.root_dir, scene_name, first_frame_idx), binocular=True)
-        first_view_path = DataLoadUtil.get_path(self.root_dir, scene_name, first_frame_idx)
-        first_left_cam_pose = first_cam_info["cam_to_world"]
-        first_center_cam_pose = first_cam_info["cam_to_world_O"]
-        first_target_point_cloud = DataLoadUtil.load_from_preprocessed_pts(first_view_path)
-        first_pts_num = first_target_point_cloud.shape[0]
-        first_downsampled_target_point_cloud = PtsUtil.random_downsample_point_cloud(first_target_point_cloud, self.pts_num)
-        first_to_world_rot_6d = PoseUtil.matrix_to_rotation_6d_numpy(np.asarray(first_left_cam_pose[:3,:3]))
-        first_to_world_trans = first_left_cam_pose[:3,3]
-        first_to_world_9d = np.concatenate([first_to_world_rot_6d, first_to_world_trans], axis=0)
-        diag = DataLoadUtil.get_bbox_diag(self.model_dir, scene_name)
-        voxel_threshold = diag*0.02
-        first_O_to_first_L_pose = np.dot(np.linalg.inv(first_left_cam_pose), first_center_cam_pose)
-        scene_path = os.path.join(self.root_dir, scene_name)
-        model_points_normals = DataLoadUtil.load_points_normals(self.root_dir, scene_name)
-
-        data_item = {
-            "first_pts_num": np.asarray(
-                first_pts_num, dtype=np.int32
-            ),
-            "first_pts": np.asarray([first_downsampled_target_point_cloud],dtype=np.float32),
-            "combined_scanned_pts": np.asarray(first_downsampled_target_point_cloud,dtype=np.float32),
-            "first_to_world_9d": np.asarray([first_to_world_9d],dtype=np.float32),
-            "scene_name": scene_name,
-            "max_coverage_rate": max_coverage_rate,
-            "voxel_threshold": voxel_threshold,
-            "filter_degree": self.filter_degree,
-            "O_to_L_pose": first_O_to_first_L_pose,
-            "first_frame_coverage": first_frame_coverage,
-            "scene_path": scene_path,
-            "model_points_normals": model_points_normals,
-            "best_seq_len": data_item_info["best_seq_len"],
-            "first_frame_id": first_frame_idx,
-        }
-        return data_item
-
-    def __len__(self):
-        return len(self.datalist)
-    
-    def get_collate_fn(self):
-        def collate_fn(batch):
-            collate_data = {}
-            collate_data["first_pts"] = [torch.tensor(item['first_pts']) for item in batch]
-            collate_data["first_to_world_9d"] = [torch.tensor(item['first_to_world_9d']) for item in batch]
-            collate_data["combined_scanned_pts"] = torch.stack([torch.tensor(item['combined_scanned_pts']) for item in batch])
-            for key in batch[0].keys():
-                if key not in ["first_pts", "first_to_world_9d", "combined_scanned_pts"]:
-                    collate_data[key] = [item[key] for item in batch]
-            return collate_data
-        return collate_fn
-
-# -------------- Debug ---------------- #
-if __name__ == "__main__":
-    import torch
-    seed = 0
-    torch.manual_seed(seed)
-    np.random.seed(seed)
-    config = {
-        "root_dir": "/home/data/hofee/project/nbv_rec/data/nbv_rec_data_512_preproc_npy",
-        "split_file": "/home/data/hofee/project/nbv_rec/data/OmniObject3d_train.txt",
-        "model_dir": "/home/data/hofee/project/nbv_rec/data/scaled_object_meshes",
-        "ratio": 0.005,
-        "batch_size": 2,
-        "filter_degree": 75,
-        "num_workers": 0,
-        "pts_num": 32684,
-        "type": namespace.Mode.TEST,
-        "load_from_preprocess": True
-    }
-    ds = SeqNBVReconstructionDataset(config)
-    print(len(ds))
-    #ds.__getitem__(10)
-    dl = ds.get_loader(shuffle=True)
-    for idx, data in enumerate(dl):
-        data = ds.process_batch(data, "cuda:0")
-        print(data)
-        # ------  Debug Start ------
-        import ipdb;ipdb.set_trace()
-        # ------  Debug End ------+

core/pipeline.py

@@ -29,6 +29,7 @@ class NBVReconstructionPipeline(nn.Module):
         
 
         self.eps = float(self.config["eps"])
+        self.enable_global_scanned_feat = self.config["global_scanned_feat"]
 
     def forward(self, data):
         mode = data["mode"]
@@ -54,7 +55,10 @@ class NBVReconstructionPipeline(nn.Module):
         return perturbed_x, random_t, target_score, std
 
     def forward_train(self, data):
+        start_time = time.time()
         main_feat = self.get_main_feat(data)
+        end_time = time.time()
+        print("get_main_feat time: ", end_time - start_time)
         """ get std """
         best_to_world_pose_9d_batch = data["best_to_world_pose_9d"]
         perturbed_x, random_t, target_score, std = self.pertube_data(
@@ -88,24 +92,23 @@ class NBVReconstructionPipeline(nn.Module):
         scanned_n_to_world_pose_9d_batch = data[
             "scanned_n_to_world_pose_9d"
         ]  # List(B): Tensor(S x 9)
-
+        scanned_pts_batch = data[
+            "scanned_pts"
+        ]
         device = next(self.parameters()).device
 
         embedding_list_batch = []
 
-        combined_scanned_pts_batch = data["combined_scanned_pts"]  # Tensor(B x N x 3)
+        for scanned_n_to_world_pose_9d, scanned_pts in zip(scanned_n_to_world_pose_9d_batch, scanned_pts_batch):
-        global_scanned_feat = self.pts_encoder.encode_points(
-            combined_scanned_pts_batch, require_per_point_feat=False
-        )  # global_scanned_feat: Tensor(B x Dg)
-
-        for scanned_n_to_world_pose_9d in scanned_n_to_world_pose_9d_batch:
             scanned_n_to_world_pose_9d = scanned_n_to_world_pose_9d.to(device)  # Tensor(S x 9)
+            scanned_pts = scanned_pts.to(device)  # Tensor(S x N x 3)
             pose_feat_seq = self.pose_encoder.encode_pose(scanned_n_to_world_pose_9d)  # Tensor(S x Dp) 
-            seq_embedding = pose_feat_seq
+            pts_feat_seq = self.pts_encoder.encode_points(scanned_pts, require_per_point_feat=False)  # Tensor(S x Dl)
-            embedding_list_batch.append(seq_embedding) # List(B): Tensor(S x (Dp))
+            seq_embedding = torch.cat([pose_feat_seq, pts_feat_seq], dim=-1) # Tensor(S x (Dp+Dl))
+            embedding_list_batch.append(seq_embedding) # List(B): Tensor(S x (Dp+Dl))
         
         seq_feat = self.seq_encoder.encode_sequence(embedding_list_batch) # Tensor(B x Ds)
-        main_feat = torch.cat([seq_feat, global_scanned_feat], dim=-1) # Tensor(B x (Ds+Dg))
+        main_feat = seq_feat # Tensor(B x Ds)
 
         if torch.isnan(main_feat).any():
             Log.error("nan in main_feat", True)

core/seq_dataset.py

@@ -2,203 +2,153 @@ import numpy as np
 from PytorchBoot.dataset import BaseDataset
 import PytorchBoot.namespace as namespace
 import PytorchBoot.stereotype as stereotype
-from PytorchBoot.config import ConfigManager
 from PytorchBoot.utils.log_util import Log
 import torch
 import os
 import sys
-
+sys.path.append(r"/home/data/hofee/project/nbv_rec/nbv_reconstruction")
-sys.path.append(r"/media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction")
 
 from utils.data_load import DataLoadUtil
 from utils.pose import PoseUtil
 from utils.pts import PtsUtil
 
-
+@stereotype.dataset("seq_nbv_reconstruction_dataset")
-@stereotype.dataset("seq_reconstruction_dataset")
+class SeqNBVReconstructionDataset(BaseDataset):
-class SeqReconstructionDataset(BaseDataset):
     def __init__(self, config):
-        super(SeqReconstructionDataset, self).__init__(config)
+        super(SeqNBVReconstructionDataset, self).__init__(config)
+        self.type = config["type"]
+        if self.type != namespace.Mode.TEST:
+            Log.error("Dataset <seq_nbv_reconstruction_dataset> Only support test mode", terminate=True)
         self.config = config
         self.root_dir = config["root_dir"]
         self.split_file_path = config["split_file"]
         self.scene_name_list = self.load_scene_name_list()
         self.datalist = self.get_datalist()
-
         self.pts_num = config["pts_num"]
-        self.type = config["type"]
+        
-        self.cache = config.get("cache")
+        self.model_dir = config["model_dir"]
+        self.filter_degree = config["filter_degree"]
         self.load_from_preprocess = config.get("load_from_preprocess", False)
         
-        if self.type == namespace.Mode.TEST:
-            #self.model_dir = config["model_dir"]
-            self.filter_degree = config["filter_degree"]
-        if self.type == namespace.Mode.TRAIN:
-            scale_ratio = 1
-            self.datalist = self.datalist*scale_ratio
-        if self.cache:
-            expr_root = ConfigManager.get("runner", "experiment", "root_dir")
-            expr_name = ConfigManager.get("runner", "experiment", "name")
-            self.cache_dir = os.path.join(expr_root, expr_name, "cache")
-            # self.preprocess_cache()
 
     def load_scene_name_list(self):
         scene_name_list = []
         with open(self.split_file_path, "r") as f:
             for line in f:
                 scene_name = line.strip()
-                if os.path.exists(os.path.join(self.root_dir, scene_name)):
                 scene_name_list.append(scene_name)
         return scene_name_list
     
-    def get_scene_name_list(self):
-        return self.scene_name_list
-
     def get_datalist(self):
         datalist = []
-        total = len(self.scene_name_list)
+        for scene_name in self.scene_name_list:
-        for idx, scene_name in enumerate(self.scene_name_list):
+            seq_num = DataLoadUtil.get_label_num(self.root_dir, scene_name)
-            print(f"processing {scene_name} ({idx}/{total})")
+            scene_max_coverage_rate = 0
             scene_max_cr_idx = 0
-            frame_len = DataLoadUtil.get_scene_seq_length(self.root_dir, scene_name)
 
-            for i in range(frame_len):
+            for seq_idx in range(seq_num):
-                path = DataLoadUtil.get_path(self.root_dir, scene_name, i)
+                label_path = DataLoadUtil.get_label_path(self.root_dir, scene_name, seq_idx)
-                pts = DataLoadUtil.load_from_preprocessed_pts(path, "npy")
+                label_data = DataLoadUtil.load_label(label_path)
-                if pts.shape[0] == 0:
+                max_coverage_rate = label_data["max_coverage_rate"]
-                    continue
+                if max_coverage_rate > scene_max_coverage_rate:
+                    scene_max_coverage_rate = max_coverage_rate
+                    scene_max_cr_idx = seq_idx
+        
+            label_path = DataLoadUtil.get_label_path(self.root_dir, scene_name, scene_max_cr_idx)
+            label_data = DataLoadUtil.load_label(label_path)
+            first_frame = label_data["best_sequence"][0]
+            best_seq_len = len(label_data["best_sequence"])
             datalist.append({
                     "scene_name": scene_name,
-                "first_frame": i,
+                    "first_frame": first_frame,
-                "best_seq_len": -1,
+                    "max_coverage_rate": scene_max_coverage_rate,
-                "max_coverage_rate": 1.0,
+                    "best_seq_len": best_seq_len,
                     "label_idx": scene_max_cr_idx,
                 })
         return datalist
 
-    def preprocess_cache(self):
-        Log.info("preprocessing cache...")
-        for item_idx in range(len(self.datalist)):
-            self.__getitem__(item_idx)
-        Log.success("finish preprocessing cache.")
-
-    def load_from_cache(self, scene_name, curr_frame_idx):
-        cache_name = f"{scene_name}_{curr_frame_idx}.txt"
-        cache_path = os.path.join(self.cache_dir, cache_name)
-        if os.path.exists(cache_path):
-            data = np.loadtxt(cache_path)
-            return data
-        else:
-            return None
-
-    def save_to_cache(self, scene_name, curr_frame_idx, data):
-        cache_name = f"{scene_name}_{curr_frame_idx}.txt"
-        cache_path = os.path.join(self.cache_dir, cache_name)
-        try:
-            np.savetxt(cache_path, data)
-        except Exception as e:
-            Log.error(f"Save cache failed: {e}")
-
-    def seq_combined_pts(self, scene, frame_idx_list):
-        all_combined_pts = []   
-        for i in frame_idx_list:
-            path = DataLoadUtil.get_path(self.root_dir, scene, i)
-            pts = DataLoadUtil.load_from_preprocessed_pts(path,"npy")
-            if pts.shape[0] == 0:
-                continue
-            all_combined_pts.append(pts)
-        all_combined_pts = np.vstack(all_combined_pts)
-        downsampled_all_pts = PtsUtil.voxel_downsample_point_cloud(all_combined_pts, 0.003)
-        return downsampled_all_pts
-
     def __getitem__(self, index):
         data_item_info = self.datalist[index]
+        first_frame_idx = data_item_info["first_frame"][0]
+        first_frame_coverage = data_item_info["first_frame"][1]
         max_coverage_rate = data_item_info["max_coverage_rate"]
-        best_seq_len = data_item_info["best_seq_len"]
         scene_name = data_item_info["scene_name"]
-        (
+        first_cam_info = DataLoadUtil.load_cam_info(DataLoadUtil.get_path(self.root_dir, scene_name, first_frame_idx), binocular=True)
-            scanned_views_pts,
+        first_view_path = DataLoadUtil.get_path(self.root_dir, scene_name, first_frame_idx)
-            scanned_coverages_rate,
+        first_left_cam_pose = first_cam_info["cam_to_world"]
-            scanned_n_to_world_pose,
+        first_center_cam_pose = first_cam_info["cam_to_world_O"]
-        ) = ([], [], [])
+        first_target_point_cloud = DataLoadUtil.load_from_preprocessed_pts(first_view_path)
-        view = data_item_info["first_frame"]
+        first_pts_num = first_target_point_cloud.shape[0]
-        frame_idx = view
+        first_downsampled_target_point_cloud = PtsUtil.random_downsample_point_cloud(first_target_point_cloud, self.pts_num)
-        view_path = DataLoadUtil.get_path(self.root_dir, scene_name, frame_idx)
+        first_to_world_rot_6d = PoseUtil.matrix_to_rotation_6d_numpy(np.asarray(first_left_cam_pose[:3,:3]))
-        cam_info = DataLoadUtil.load_cam_info(view_path, binocular=True)
+        first_to_world_trans = first_left_cam_pose[:3,3]
-        
+        first_to_world_9d = np.concatenate([first_to_world_rot_6d, first_to_world_trans], axis=0)
-        n_to_world_pose = cam_info["cam_to_world"]  
+        diag = DataLoadUtil.get_bbox_diag(self.model_dir, scene_name)
-        target_point_cloud = (
+        voxel_threshold = diag*0.02
-            DataLoadUtil.load_from_preprocessed_pts(view_path)
-        )
-        downsampled_target_point_cloud = PtsUtil.random_downsample_point_cloud(
-            target_point_cloud, self.pts_num
-        )
-        scanned_views_pts.append(downsampled_target_point_cloud)
-        
-        n_to_world_6d = PoseUtil.matrix_to_rotation_6d_numpy(
-            np.asarray(n_to_world_pose[:3, :3])
-        ) 
-        first_left_cam_pose = cam_info["cam_to_world"]
-        first_center_cam_pose = cam_info["cam_to_world_O"]
         first_O_to_first_L_pose = np.dot(np.linalg.inv(first_left_cam_pose), first_center_cam_pose)
-        n_to_world_trans = n_to_world_pose[:3, 3]
+        scene_path = os.path.join(self.root_dir, scene_name)
-        n_to_world_9d = np.concatenate([n_to_world_6d, n_to_world_trans], axis=0)
+        model_points_normals = DataLoadUtil.load_points_normals(self.root_dir, scene_name)
-        scanned_n_to_world_pose.append(n_to_world_9d)
 
-        frame_list = []
-        for i in range(DataLoadUtil.get_scene_seq_length(self.root_dir, scene_name)):
-            frame_list.append(i)
-        gt_pts = self.seq_combined_pts(scene_name, frame_list)
         data_item = {
-            "first_scanned_pts": np.asarray(scanned_views_pts, dtype=np.float32), # Ndarray(S x Nv x 3)
+            "first_pts_num": np.asarray(
-            "first_scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9)
+                first_pts_num, dtype=np.int32
-            "seq_max_coverage_rate": max_coverage_rate, # Float, range(0, 1)
+            ),
-            "best_seq_len": best_seq_len, # Int
+            "first_pts": np.asarray([first_downsampled_target_point_cloud],dtype=np.float32),
-            "scene_name": scene_name, # String
+            "combined_scanned_pts": np.asarray(first_downsampled_target_point_cloud,dtype=np.float32),
-            "gt_pts": gt_pts, # Ndarray(N x 3)
+            "first_to_world_9d": np.asarray([first_to_world_9d],dtype=np.float32),
-            "scene_path": os.path.join(self.root_dir, scene_name), # String
+            "scene_name": scene_name,
+            "max_coverage_rate": max_coverage_rate,
+            "voxel_threshold": voxel_threshold,
+            "filter_degree": self.filter_degree,
             "O_to_L_pose": first_O_to_first_L_pose,
+            "first_frame_coverage": first_frame_coverage,
+            "scene_path": scene_path,
+            "model_points_normals": model_points_normals,
+            "best_seq_len": data_item_info["best_seq_len"],
+            "first_frame_id": first_frame_idx,
         }
-
         return data_item
 
     def __len__(self):
         return len(self.datalist)
     
+    def get_collate_fn(self):
+        def collate_fn(batch):
+            collate_data = {}
+            collate_data["first_pts"] = [torch.tensor(item['first_pts']) for item in batch]
+            collate_data["first_to_world_9d"] = [torch.tensor(item['first_to_world_9d']) for item in batch]
+            collate_data["combined_scanned_pts"] = torch.stack([torch.tensor(item['combined_scanned_pts']) for item in batch])
+            for key in batch[0].keys():
+                if key not in ["first_pts", "first_to_world_9d", "combined_scanned_pts"]:
+                    collate_data[key] = [item[key] for item in batch]
+            return collate_data
+        return collate_fn
 
 # -------------- Debug ---------------- #
 if __name__ == "__main__":
-    #import ipdb; ipdb.set_trace()
     import torch
-    from tqdm import tqdm
-    import pickle
-    import os
-
     seed = 0
     torch.manual_seed(seed)
     np.random.seed(seed)
-    
     config = {
-        "root_dir": "/media/hofee/data/data/new_testset",
+        "root_dir": "/home/data/hofee/project/nbv_rec/data/nbv_rec_data_512_preproc_npy",
-        "source": "seq_reconstruction_dataset",
+        "split_file": "/home/data/hofee/project/nbv_rec/data/OmniObject3d_train.txt",
-        "split_file": "/media/hofee/data/data/OmniObject3d_test.txt",
+        "model_dir": "/home/data/hofee/project/nbv_rec/data/scaled_object_meshes",
-        "load_from_preprocess": True,
+        "ratio": 0.005,
+        "batch_size": 2,
         "filter_degree": 75,
         "num_workers": 0,
-        "pts_num": 8192,
+        "pts_num": 32684,
         "type": namespace.Mode.TEST,
+        "load_from_preprocess": True
     }
-    
+    ds = SeqNBVReconstructionDataset(config)
-    output_dir = "/media/hofee/data/data/new_testset_output"
+    print(len(ds))
-    os.makedirs(output_dir, exist_ok=True)
+    #ds.__getitem__(10)
-
+    dl = ds.get_loader(shuffle=True)
-    ds = SeqReconstructionDataset(config)
+    for idx, data in enumerate(dl):
-    for i in tqdm(range(len(ds)), desc="processing dataset"):
+        data = ds.process_batch(data, "cuda:0")
-        output_path = os.path.join(output_dir, f"item_{i}.pkl")
+        print(data)
-        item = ds.__getitem__(i)
+        # ------  Debug Start ------
-        for key, value in item.items():
+        import ipdb;ipdb.set_trace()
-            if isinstance(value, np.ndarray):
+        # ------  Debug End ------+
-                item[key] = value.tolist()
-        import ipdb; ipdb.set_trace()
-        with open(output_path, "wb") as f:
-            pickle.dump(item, f)

core/seq_dataset_preprocessed.py

@@ -1,84 +0,0 @@
-import numpy as np
-from PytorchBoot.dataset import BaseDataset
-import PytorchBoot.namespace as namespace
-import PytorchBoot.stereotype as stereotype
-from PytorchBoot.config import ConfigManager
-from PytorchBoot.utils.log_util import Log
-import pickle
-import torch
-import os
-import sys
-
-sys.path.append(r"C:\Document\Local Project\nbv_rec\nbv_reconstruction")
-
-from utils.data_load import DataLoadUtil
-from utils.pose import PoseUtil
-from utils.pts import PtsUtil
-
-
-@stereotype.dataset("seq_reconstruction_dataset_preprocessed")
-class SeqReconstructionDatasetPreprocessed(BaseDataset):
-    def __init__(self, config):
-        super(SeqReconstructionDatasetPreprocessed, self).__init__(config)
-        self.config = config
-        self.root_dir = config["root_dir"]
-        self.real_root_dir = r"/media/hofee/data/data/new_testset"
-        self.item_list = os.listdir(self.root_dir)
-
-    def __getitem__(self, index):
-        data = pickle.load(open(os.path.join(self.root_dir, self.item_list[index]), "rb"))
-        data_item = {
-            "first_scanned_pts": np.asarray(data["first_scanned_pts"], dtype=np.float32), # Ndarray(S x Nv x 3)
-            "first_scanned_n_to_world_pose_9d": np.asarray(data["first_scanned_n_to_world_pose_9d"], dtype=np.float32), # Ndarray(S x 9)
-            "seq_max_coverage_rate": data["seq_max_coverage_rate"], # Float, range(0, 1)
-            "best_seq_len": data["best_seq_len"], # Int
-            "scene_name": data["scene_name"], # String
-            "gt_pts": np.asarray(data["gt_pts"], dtype=np.float32), # Ndarray(N x 3)
-            "scene_path": os.path.join(self.real_root_dir, data["scene_name"]), # String
-            "O_to_L_pose": np.asarray(data["O_to_L_pose"], dtype=np.float32),
-        }
-        return data_item
-
-    def __len__(self):
-        return len(self.item_list)
-
-
-# -------------- Debug ---------------- #
-if __name__ == "__main__":
-    import torch
-
-    seed = 0
-    torch.manual_seed(seed)
-    np.random.seed(seed)
-    '''
-    OmniObject3d_test:
-    root_dir: "H:\\AI\\Datasets\\packed_test_data"
-    model_dir: "H:\\AI\\Datasets\\scaled_object_meshes"
-    source: seq_reconstruction_dataset
-    split_file: "H:\\AI\\Datasets\\data_list\\OmniObject3d_test.txt"
-    type: test
-    filter_degree: 75
-    eval_list:
-      - pose_diff
-      - coverage_rate_increase
-    ratio: 0.1
-    batch_size: 1
-    num_workers: 12
-    pts_num: 8192
-    load_from_preprocess: True
-    '''
-    config = {
-        "root_dir": "H:\\AI\\Datasets\\packed_test_data",
-        "source": "seq_reconstruction_dataset",
-        "split_file": "H:\\AI\\Datasets\\data_list\\OmniObject3d_test.txt",
-        "load_from_preprocess": True,
-        "ratio": 1,
-        "filter_degree": 75,
-        "num_workers": 0,
-        "pts_num": 8192,
-        "type": "test",
-    }
-    ds = SeqReconstructionDataset(config)
-    print(len(ds))
-    print(ds.__getitem__(10))
-    

preprocess/pack_upload_data.py

@@ -29,8 +29,8 @@ def pack_all_scenes(root, scene_list, output_dir):
         pack_scene_data(root, scene, output_dir)
 
 if __name__ == "__main__":
-    root = r"/media/hofee/repository/data_part_1"
+    root = r"H:\AI\Datasets\nbv_rec_part2"
-    output_dir = r"/media/hofee/repository/upload_part1"
+    output_dir = r"H:\AI\Datasets\upload_part2"
     scene_list = os.listdir(root)
     from_idx = 0
     to_idx = len(scene_list)

preprocess/preprocessor.py

@@ -164,10 +164,10 @@ def save_scene_data(root, scene, scene_idx=0, scene_total=1,file_type="txt"):
 
 if __name__ == "__main__":
     #root = "/media/hofee/repository/new_data_with_normal"
-    root = "/media/hofee/data/data/new_testset"
+    root = r"H:\AI\Datasets\nbv_rec_part2"
     scene_list = os.listdir(root)
     from_idx = 0 # 1000
-    to_idx = len(scene_list) # 1500
+    to_idx = 600 # 1500
 
 
     cnt = 0
@@ -179,11 +179,7 @@ if __name__ == "__main__":
             print(f"Scene {scene} has been processed")
             cnt+=1
             continue
-        try:
         save_scene_data(root, scene, cnt, total, file_type="npy")
-        except Exception as e:
-            print(f"Error occurred when processing scene {scene}")
-            print(e)
         cnt+=1
         end = time.time()
         print(f"Time cost: {end-start}")

runners/inferece_server.py

@@ -13,7 +13,7 @@ from PytorchBoot.utils import Log
 
 from utils.pts import PtsUtil
 
-@stereotype.runner("inferencer_server")
+@stereotype.runner("inferencer")
 class InferencerServer(Runner):
     def __init__(self, config_path):
         super().__init__(config_path)
@@ -24,10 +24,9 @@ class InferencerServer(Runner):
         self.pipeline_name = self.config[namespace.Stereotype.PIPELINE]
         self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
         self.pipeline = self.pipeline.to(self.device)
-        self.pts_num = 8192
             
         ''' Experiment '''
-        self.load_experiment("inferencer_server")
+        self.load_experiment("nbv_evaluator")
 
     def get_input_data(self, data):
         input_data = {}
@@ -37,36 +36,28 @@ class InferencerServer(Runner):
         fps_downsampled_combined_scanned_pts, fps_idx = PtsUtil.fps_downsample_point_cloud(
             combined_scanned_views_pts, self.pts_num, require_idx=True
         )
-        # combined_scanned_views_pts_mask = np.zeros(len(scanned_pts), dtype=np.uint8)
+        combined_scanned_views_pts_mask = np.zeros(len(scanned_pts), dtype=np.uint8)
-        # start_idx = 0
+        start_idx = 0
-        # for i in range(len(scanned_pts)):
+        for i in range(len(scanned_pts)):
-        #     end_idx = start_idx + len(scanned_pts[i])
+            end_idx = start_idx + len(scanned_pts[i])
-        #     combined_scanned_views_pts_mask[start_idx:end_idx] = i
+            combined_scanned_views_pts_mask[start_idx:end_idx] = i
-        #     start_idx = end_idx
+            start_idx = end_idx
 
-        # fps_downsampled_combined_scanned_pts_mask = combined_scanned_views_pts_mask[fps_idx]
+        fps_downsampled_combined_scanned_pts_mask = combined_scanned_views_pts_mask[fps_idx]
 
-        input_data["scanned_pts"] = scanned_pts
+        input_data["scanned_pts_mask"] = np.asarray(fps_downsampled_combined_scanned_pts_mask, dtype=np.uint8)
-        # input_data["scanned_pts_mask"] = np.asarray(fps_downsampled_combined_scanned_pts_mask, dtype=np.uint8)
         input_data["scanned_n_to_world_pose_9d"] = np.asarray(scanned_n_to_world_pose_9d, dtype=np.float32)
         input_data["combined_scanned_pts"] = np.asarray(fps_downsampled_combined_scanned_pts, dtype=np.float32)
         return input_data
     
     def get_result(self, output_data):
 
-        pred_pose_9d = output_data["pred_pose_9d"]
+        estimated_delta_rot_9d = output_data["pred_pose_9d"]
         result = {
-            "pred_pose_9d": pred_pose_9d.tolist()
+            "estimated_delta_rot_9d": estimated_delta_rot_9d.tolist()
         }
         return result
     
-    def collate_input(self, input_data):
-        collated_input_data = {}
-        collated_input_data["scanned_pts"] = [torch.tensor(input_data["scanned_pts"], dtype=torch.float32, device=self.device)]
-        collated_input_data["scanned_n_to_world_pose_9d"] = [torch.tensor(input_data["scanned_n_to_world_pose_9d"], dtype=torch.float32, device=self.device)]
-        collated_input_data["combined_scanned_pts"] = torch.tensor(input_data["combined_scanned_pts"], dtype=torch.float32, device=self.device).unsqueeze(0)
-        return collated_input_data
-    
     def run(self):
         Log.info("Loading from epoch {}.".format(self.current_epoch))
     
@@ -74,8 +65,7 @@ class InferencerServer(Runner):
         def inference():
             data = request.json
             input_data = self.get_input_data(data)
-            collated_input_data = self.collate_input(input_data)
+            output_data = self.pipeline.forward_test(input_data)
-            output_data = self.pipeline.forward_test(collated_input_data)
             result = self.get_result(output_data)
             return jsonify(result)
         

runners/inferencer.py

@@ -19,7 +19,7 @@ from PytorchBoot.dataset import BaseDataset
 from PytorchBoot.runners.runner import Runner
 from PytorchBoot.utils import Log
 from PytorchBoot.status import status_manager
-from utils.data_load import DataLoadUtil
+
 @stereotype.runner("inferencer")
 class Inferencer(Runner):
     def __init__(self, config_path):
@@ -27,7 +27,6 @@ class Inferencer(Runner):
     
         self.script_path = ConfigManager.get(namespace.Stereotype.RUNNER, "blender_script_path")
         self.output_dir = ConfigManager.get(namespace.Stereotype.RUNNER, "output_dir")
-        self.voxel_size = ConfigManager.get(namespace.Stereotype.RUNNER, "voxel_size")
         ''' Pipeline '''
         self.pipeline_name = self.config[namespace.Stereotype.PIPELINE]
         self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
@@ -35,11 +34,6 @@ class Inferencer(Runner):
             
         ''' Experiment '''
         self.load_experiment("nbv_evaluator")
-        self.stat_result_path = os.path.join(self.output_dir, "stat.json")
-        if os.path.exists(self.stat_result_path):
-            with open(self.stat_result_path, "r") as f:
-                self.stat_result = json.load(f)
-        else:
         self.stat_result = {}
 
         ''' Test '''
@@ -71,71 +65,59 @@ class Inferencer(Runner):
             for dataset_idx, test_set in enumerate(self.test_set_list):
                 status_manager.set_progress("inference", "inferencer", f"dataset", dataset_idx, len(self.test_set_list))
                 test_set_name = test_set.get_name()
+                test_loader = test_set.get_loader()
 
-                total=int(len(test_set))
+                if test_loader.batch_size > 1:
-                for i in tqdm(range(total), desc=f"Processing {test_set_name}", ncols=100):
+                    Log.error("Batch size should be 1 for inference, found {} in {}".format(test_loader.batch_size, test_set_name), terminate=True)
-                    data = test_set.__getitem__(i)
-                    scene_name = data["scene_name"]
-                    if scene_name != "omniobject3d-book_004":
-                        continue
-                    inference_result_path = os.path.join(self.output_dir, test_set_name, f"{scene_name}.pkl")
-                    if os.path.exists(inference_result_path):
-                        Log.info(f"Inference result already exists for scene: {scene_name}")
-                        continue
 
+                total=int(len(test_loader))
+                loop = tqdm(enumerate(test_loader), total=total)
+                for i, data in loop:
                     status_manager.set_progress("inference", "inferencer", f"Batch[{test_set_name}]", i+1, total)
+                    test_set.process_batch(data, self.device)
                     output = self.predict_sequence(data)
-                    self.save_inference_result(test_set_name, data["scene_name"], output)
+                    self.save_inference_result(test_set_name, data["scene_name"][0], output)
                     
             status_manager.set_progress("inference", "inferencer", f"dataset", len(self.test_set_list), len(self.test_set_list))
         
-    def predict_sequence(self, data, cr_increase_threshold=0, overlap_area_threshold=25, scan_points_threshold=10, max_iter=50, max_retry = 5):
+    def predict_sequence(self, data, cr_increase_threshold=0, max_iter=50, max_retry=5):
-        scene_name = data["scene_name"]
+        scene_name = data["scene_name"][0]
         Log.info(f"Processing scene: {scene_name}")
         status_manager.set_status("inference", "inferencer", "scene", scene_name)
 
         ''' data for rendering '''
-        scene_path = data["scene_path"]
+        scene_path = data["scene_path"][0]
-        O_to_L_pose = data["O_to_L_pose"]
+        O_to_L_pose = data["O_to_L_pose"][0]
-        voxel_threshold = self.voxel_size
+        voxel_threshold = data["voxel_threshold"][0]
-        filter_degree = 75
+        filter_degree = data["filter_degree"][0]
-        down_sampled_model_pts = data["gt_pts"]
+        model_points_normals = data["model_points_normals"][0]
-        
+        model_pts = model_points_normals[:,:3]
-        first_frame_to_world_9d = data["first_scanned_n_to_world_pose_9d"][0]
+        down_sampled_model_pts = PtsUtil.voxel_downsample_point_cloud(model_pts, voxel_threshold)
-        first_frame_to_world = np.eye(4)
+        first_frame_to_world_9d = data["first_to_world_9d"][0]
-        first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_numpy(first_frame_to_world_9d[:6])
+        first_frame_to_world = torch.eye(4, device=first_frame_to_world_9d.device)
-        first_frame_to_world[:3,3] = first_frame_to_world_9d[6:]
+        first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_tensor_batch(first_frame_to_world_9d[:,:6])[0]
+        first_frame_to_world[:3,3] = first_frame_to_world_9d[0,6:]
+        first_frame_to_world = first_frame_to_world.to(self.device)
         
         ''' data for inference '''
         input_data = {}
-        input_data["combined_scanned_pts"] = torch.tensor(data["first_scanned_pts"][0], dtype=torch.float32).to(self.device).unsqueeze(0)
+        input_data["scanned_pts"] = [data["first_pts"][0].to(self.device)]
-        input_data["scanned_n_to_world_pose_9d"] = [torch.tensor(data["first_scanned_n_to_world_pose_9d"], dtype=torch.float32).to(self.device)]
+        input_data["scanned_n_to_world_pose_9d"] = [data["first_to_world_9d"][0].to(self.device)]
         input_data["mode"] = namespace.Mode.TEST
-        input_pts_N = input_data["combined_scanned_pts"].shape[1]
+        input_data["combined_scanned_pts"] = data["combined_scanned_pts"]
+        input_pts_N = input_data["scanned_pts"][0].shape[1]
         
-        root = os.path.dirname(scene_path)
+        first_frame_target_pts, _ = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, model_points_normals, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
-        
-        display_table_info = DataLoadUtil.get_display_table_info(root, scene_name)
-        radius = display_table_info["radius"]
-        scan_points = np.asarray(ReconstructionUtil.generate_scan_points(display_table_top=0,display_table_radius=radius))
-
-        first_frame_target_pts, first_frame_target_normals, first_frame_scan_points_indices = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, scan_points, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
         scanned_view_pts = [first_frame_target_pts]
-        history_indices = [first_frame_scan_points_indices]
+        last_pred_cr = self.compute_coverage_rate(scanned_view_pts, None, down_sampled_model_pts, threshold=voxel_threshold)
-        last_pred_cr, added_pts_num = self.compute_coverage_rate(scanned_view_pts, None, down_sampled_model_pts, threshold=voxel_threshold)
+
         retry_duplication_pose = []
         retry_no_pts_pose = []
-        retry_overlap_pose = []
         retry = 0
         pred_cr_seq = [last_pred_cr]
-        success = 0
-        last_pts_num = PtsUtil.voxel_downsample_point_cloud(data["first_scanned_pts"][0], 0.002).shape[0]
-        import time
         while len(pred_cr_seq) < max_iter and retry < max_retry:
-            start_time = time.time()
+            
             output = self.pipeline(input_data)
-            end_time = time.time()
-            print(f"Time taken for inference: {end_time - start_time} seconds")
             pred_pose_9d = output["pred_pose_9d"]
             pred_pose = torch.eye(4, device=pred_pose_9d.device)
 
@@ -143,24 +125,7 @@ class Inferencer(Runner):
             pred_pose[:3,3] = pred_pose_9d[0,6:]
             
             try:
-                start_time = time.time()
+                new_target_pts_world, new_pts_world = RenderUtil.render_pts(pred_pose, scene_path, self.script_path, model_points_normals, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose, require_full_scene=True)
-                new_target_pts, new_target_normals, new_scan_points_indices = RenderUtil.render_pts(pred_pose, scene_path, self.script_path, scan_points, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
-                #import ipdb; ipdb.set_trace()
-                if not ReconstructionUtil.check_scan_points_overlap(history_indices, new_scan_points_indices, scan_points_threshold):
-                    curr_overlap_area_threshold = overlap_area_threshold
-                else:
-                    curr_overlap_area_threshold = overlap_area_threshold * 0.5  
-
-                downsampled_new_target_pts = PtsUtil.voxel_downsample_point_cloud(new_target_pts, voxel_threshold)
-                overlap, _ = ReconstructionUtil.check_overlap(downsampled_new_target_pts, down_sampled_model_pts, overlap_area_threshold = curr_overlap_area_threshold, voxel_size=voxel_threshold, require_new_added_pts_num = True)
-                if not overlap:
-                    retry += 1
-                    retry_overlap_pose.append(pred_pose.cpu().numpy().tolist())
-                    continue
-                
-                history_indices.append(new_scan_points_indices)
-                end_time = time.time()
-                print(f"Time taken for rendering: {end_time - start_time} seconds")
             except Exception as e:
                 Log.warning(f"Error in scene {scene_path}, {e}")
                 print("current pose: ", pred_pose)
@@ -169,42 +134,61 @@ class Inferencer(Runner):
                 retry += 1
                 continue
             
-            if new_target_pts.shape[0] == 0:
+            
-                print("no pts in new target")
+            pred_cr = self.compute_coverage_rate(scanned_view_pts, new_target_pts_world, down_sampled_model_pts, threshold=voxel_threshold)
-                retry_no_pts_pose.append(pred_pose.cpu().numpy().tolist())
+            
+            print(pred_cr, last_pred_cr, " max: ", data["max_coverage_rate"])
+            if pred_cr >= data["max_coverage_rate"]:
+                print("max coverage rate reached!")
+            if pred_cr <= last_pred_cr + cr_increase_threshold:
                 retry += 1
+                retry_duplication_pose.append(pred_pose.cpu().numpy().tolist())
                 continue
 
-            start_time = time.time()
-            pred_cr, _ = self.compute_coverage_rate(scanned_view_pts, new_target_pts, down_sampled_model_pts, threshold=voxel_threshold)
-            end_time = time.time()
-            print(f"Time taken for coverage rate computation: {end_time - start_time} seconds")
-            print(pred_cr, last_pred_cr, " max: ", data["seq_max_coverage_rate"])
-            if pred_cr >= data["seq_max_coverage_rate"] - 1e-3:
-                print("max coverage rate reached!: ", pred_cr)
-                success += 1
-        
-
             retry = 0
             pred_cr_seq.append(pred_cr)
-            scanned_view_pts.append(new_target_pts)
+            scanned_view_pts.append(new_target_pts_world)
+            down_sampled_new_pts_world = PtsUtil.random_downsample_point_cloud(new_pts_world, input_pts_N)
+            new_pts_world_aug = np.hstack([down_sampled_new_pts_world, np.ones((down_sampled_new_pts_world.shape[0], 1))])
+            new_pts = np.dot(np.linalg.inv(first_frame_to_world.cpu()), new_pts_world_aug.T).T[:,:3]
 
+            new_pts_tensor = torch.tensor(new_pts, dtype=torch.float32).unsqueeze(0).to(self.device)
+            
+            input_data["scanned_pts"] = [torch.cat([input_data["scanned_pts"][0] , new_pts_tensor], dim=0)]
             input_data["scanned_n_to_world_pose_9d"] = [torch.cat([input_data["scanned_n_to_world_pose_9d"][0], pred_pose_9d], dim=0)]
-            
+            combined_scanned_views_pts = np.concatenate(input_data["scanned_pts"][0].tolist(), axis=0)
-            combined_scanned_pts = np.vstack(scanned_view_pts)
+            voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_views_pts, 0.002)
-            voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_pts, 0.002)
             random_downsampled_combined_scanned_pts_np = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, input_pts_N)
             input_data["combined_scanned_pts"] = torch.tensor(random_downsampled_combined_scanned_pts_np, dtype=torch.float32).unsqueeze(0).to(self.device)
 
-            if success > 3:
+            
-                break
             last_pred_cr = pred_cr
-            pts_num = voxel_downsampled_combined_scanned_pts_np.shape[0]
+
-            if pts_num - last_pts_num < 10 and pred_cr < data["seq_max_coverage_rate"] - 1e-3:
+        
-                retry += 1
+        input_data["scanned_pts"] = input_data["scanned_pts"][0].cpu().numpy().tolist()
-                retry_duplication_pose.append(pred_pose.cpu().numpy().tolist())
+        input_data["scanned_n_to_world_pose_9d"] = input_data["scanned_n_to_world_pose_9d"][0].cpu().numpy().tolist()
-                print("delta pts num < 10:", pts_num, last_pts_num)
+        result = {
-            last_pts_num = pts_num
+            "pred_pose_9d_seq": input_data["scanned_n_to_world_pose_9d"],
+            "pts_seq": input_data["scanned_pts"],
+            "target_pts_seq": scanned_view_pts,
+            "coverage_rate_seq": pred_cr_seq,
+            "max_coverage_rate": data["max_coverage_rate"][0],
+            "pred_max_coverage_rate": max(pred_cr_seq),
+            "scene_name": scene_name,
+            "retry_no_pts_pose": retry_no_pts_pose,
+            "retry_duplication_pose": retry_duplication_pose,
+            "best_seq_len": data["best_seq_len"][0],
+        }
+        self.stat_result[scene_name] = {
+            "max_coverage_rate": data["max_coverage_rate"][0],
+            "success_rate": max(pred_cr_seq)/ data["max_coverage_rate"][0],
+            "coverage_rate_seq": pred_cr_seq,
+            "pred_max_coverage_rate": max(pred_cr_seq),
+            "pred_seq_len": len(pred_cr_seq),
+        }
+        print('success rate: ', max(pred_cr_seq) / data["max_coverage_rate"][0])
+
+        return result
 
     def compute_coverage_rate(self, scanned_view_pts, new_pts, model_pts, threshold=0.005):
         if new_pts is not None:
@@ -222,7 +206,7 @@ class Inferencer(Runner):
             os.makedirs(dataset_dir)
         output_path = os.path.join(dataset_dir, f"{scene_name}.pkl")
         pickle.dump(output, open(output_path, "wb"))
-        with open(self.stat_result_path, "w") as f:
+        with open(os.path.join(dataset_dir, "stat.json"), "w") as f:
             json.dump(self.stat_result, f)
     
 

utils/data_load.py

@@ -24,6 +24,8 @@ class DataLoadUtil:
         for channel in float_channels:
             channel_data = exr_file.channel(channel)
             img_data.append(np.frombuffer(channel_data, dtype=np.float16).reshape((height, width)))
+
+        # 将各通道组合成一个 (height, width, 3) 的 RGB 图像
         img = np.stack(img_data, axis=-1)
         return img
 

utils/pts.py

@@ -17,17 +17,6 @@ class PtsUtil:
             unique_voxels = np.unique(voxel_indices, axis=0, return_inverse=True)
             return unique_voxels[0]*voxel_size
     
-    @staticmethod
-    def voxel_downsample_point_cloud_random(point_cloud, voxel_size=0.005, require_idx=False):
-        voxel_indices = np.floor(point_cloud / voxel_size).astype(np.int32)
-        unique_voxels, inverse, counts = np.unique(voxel_indices, axis=0, return_inverse=True, return_counts=True)
-        idx_sort = np.argsort(inverse)
-        idx_unique = idx_sort[np.cumsum(counts)-counts]
-        downsampled_points = point_cloud[idx_unique]
-        if require_idx:
-            return downsampled_points, inverse
-        return downsampled_points
-    
     @staticmethod
     def random_downsample_point_cloud(point_cloud, num_points, require_idx=False):
         if point_cloud.shape[0] == 0:

utils/reconstruction.py

@@ -32,15 +32,13 @@ class ReconstructionUtil:
         
     
     @staticmethod
-    def check_overlap(new_point_cloud, combined_point_cloud, overlap_area_threshold=25, voxel_size=0.01, require_new_added_pts_num=False):
+    def check_overlap(new_point_cloud, combined_point_cloud, overlap_area_threshold=25, voxel_size=0.01):
         kdtree = cKDTree(combined_point_cloud)
         distances, _ = kdtree.query(new_point_cloud)
-        overlapping_points_num = np.sum(distances < voxel_size*2)
+        overlapping_points = np.sum(distances < voxel_size*2)
         cm = 0.01
         voxel_size_cm = voxel_size / cm
-        overlap_area = overlapping_points_num * voxel_size_cm * voxel_size_cm
+        overlap_area = overlapping_points * voxel_size_cm * voxel_size_cm
-        if require_new_added_pts_num:
-            return overlap_area > overlap_area_threshold, len(new_point_cloud)-np.sum(distances < voxel_size*1.2)
         return overlap_area > overlap_area_threshold
 
 

utils/render.py

@@ -1,75 +1,16 @@
 
 import os
 import json
-import time
 import subprocess
 import tempfile
 import shutil
-import numpy as np
 from utils.data_load import DataLoadUtil
 from utils.reconstruction import ReconstructionUtil
 from utils.pts import PtsUtil
 class RenderUtil:
-    target_mask_label = (0, 255, 0)
-    display_table_mask_label = (0, 0, 255)
-    random_downsample_N = 32768
-    min_z = 0.2
-    max_z = 0.5
 
     @staticmethod
-    def get_world_points_and_normal(depth, mask, normal, cam_intrinsic, cam_extrinsic, random_downsample_N):
+    def render_pts(cam_pose, scene_path, script_path, model_points_normals, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
-        z = depth[mask]
-        i, j = np.nonzero(mask)
-        x = (j - cam_intrinsic[0, 2]) * z / cam_intrinsic[0, 0]
-        y = (i - cam_intrinsic[1, 2]) * z / cam_intrinsic[1, 1]
-
-        points_camera = np.stack((x, y, z), axis=-1).reshape(-1, 3)
-        normal_camera = normal[mask].reshape(-1, 3)
-        sampled_target_points, idx = PtsUtil.random_downsample_point_cloud(
-                    points_camera, random_downsample_N, require_idx=True
-                )
-        if len(sampled_target_points) == 0:
-            return np.zeros((0, 3)), np.zeros((0, 3))
-        sampled_normal_camera  = normal_camera[idx]
-
-        points_camera_aug = np.concatenate((sampled_target_points, np.ones((sampled_target_points.shape[0], 1))), axis=-1)
-        points_camera_world = np.dot(cam_extrinsic, points_camera_aug.T).T[:, :3]
-        
-        return points_camera_world, sampled_normal_camera
-    
-    @staticmethod
-    def get_world_points(depth, mask, cam_intrinsic, cam_extrinsic, random_downsample_N):
-        z = depth[mask]
-        i, j = np.nonzero(mask)
-        x = (j - cam_intrinsic[0, 2]) * z / cam_intrinsic[0, 0]
-        y = (i - cam_intrinsic[1, 2]) * z / cam_intrinsic[1, 1]
-
-        points_camera = np.stack((x, y, z), axis=-1).reshape(-1, 3)
-        sampled_target_points = PtsUtil.random_downsample_point_cloud(
-                    points_camera, random_downsample_N
-                )
-        points_camera_aug = np.concatenate((sampled_target_points, np.ones((sampled_target_points.shape[0], 1))), axis=-1)
-        points_camera_world = np.dot(cam_extrinsic, points_camera_aug.T).T[:, :3]
-        
-        return points_camera_world
-    
-    @staticmethod
-    def get_scan_points_indices(scan_points, mask, display_table_mask_label, cam_intrinsic, cam_extrinsic):
-        scan_points_homogeneous = np.hstack((scan_points, np.ones((scan_points.shape[0], 1))))
-        points_camera = np.dot(np.linalg.inv(cam_extrinsic), scan_points_homogeneous.T).T[:, :3]
-        points_image_homogeneous = np.dot(cam_intrinsic, points_camera.T).T
-        points_image_homogeneous /= points_image_homogeneous[:, 2:]
-        pixel_x = points_image_homogeneous[:, 0].astype(int)
-        pixel_y = points_image_homogeneous[:, 1].astype(int)
-        h, w = mask.shape[:2]
-        valid_indices = (pixel_x >= 0) & (pixel_x < w) & (pixel_y >= 0) & (pixel_y < h)
-        mask_colors = mask[pixel_y[valid_indices], pixel_x[valid_indices]]
-        selected_points_indices = np.where((mask_colors == display_table_mask_label).all(axis=-1))[0]
-        selected_points_indices = np.where(valid_indices)[0][selected_points_indices]
-        return selected_points_indices
-
-    @staticmethod
-    def render_pts(cam_pose, scene_path, script_path, scan_points, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
         
         nO_to_world_pose = DataLoadUtil.get_real_cam_O_from_cam_L(cam_pose, nO_to_nL_pose, scene_path=scene_path)
 
@@ -84,58 +25,28 @@ class RenderUtil:
             params_data_path = os.path.join(temp_dir, "params.json")
             with open(params_data_path, 'w') as f:
                 json.dump(params, f)
-            start_time = time.time()
             result = subprocess.run([
-                '/home/hofee/blender-4.0.2-linux-x64/blender', '-b', '-P', script_path, '--', temp_dir
+                'blender', '-b', '-P', script_path, '--', temp_dir
             ], capture_output=True, text=True)
-            end_time = time.time()
+            if result.returncode != 0:
-
+                print("Blender script failed:")
-            print(f"-- Time taken for blender: {end_time - start_time} seconds")
+                print(result.stderr)
+                return None
             path = os.path.join(temp_dir, "tmp")
-            cam_info = DataLoadUtil.load_cam_info(path, binocular=True)
+            point_cloud = DataLoadUtil.get_target_point_cloud_world_from_path(path, binocular=True)
-            depth_L, depth_R = DataLoadUtil.load_depth(
+            cam_params = DataLoadUtil.load_cam_info(path, binocular=True)
-                    path, cam_info["near_plane"], 
-                    cam_info["far_plane"], 
-                    binocular=True
-                )
-            start_time = time.time()
-            mask_L, mask_R = DataLoadUtil.load_seg(path, binocular=True)
-            normal_L = DataLoadUtil.load_normal(path, binocular=True, left_only=True)
-            ''' target points '''
-            mask_img_L = mask_L
-            mask_img_R = mask_R
             
-            target_mask_img_L = (mask_L == RenderUtil.target_mask_label).all(axis=-1)
+            ''' TODO: old code: filter_points api is changed, need to update the code '''
-            target_mask_img_R = (mask_R == RenderUtil.target_mask_label).all(axis=-1)
+            filtered_point_cloud = PtsUtil.filter_points(point_cloud, model_points_normals, cam_pose=cam_params["cam_to_world"], voxel_size=voxel_threshold, theta=filter_degree)
+            full_scene_point_cloud = None
+            if require_full_scene:
+                depth_L, depth_R = DataLoadUtil.load_depth(path, cam_params['near_plane'], cam_params['far_plane'], binocular=True)
+                point_cloud_L = DataLoadUtil.get_point_cloud(depth_L, cam_params['cam_intrinsic'], cam_params['cam_to_world'])['points_world']
+                point_cloud_R = DataLoadUtil.get_point_cloud(depth_R, cam_params['cam_intrinsic'], cam_params['cam_to_world_R'])['points_world']
+            
+                point_cloud_L = PtsUtil.random_downsample_point_cloud(point_cloud_L, 65536)
+                point_cloud_R = PtsUtil.random_downsample_point_cloud(point_cloud_R, 65536)
+                full_scene_point_cloud = PtsUtil.get_overlapping_points(point_cloud_L, point_cloud_R)
 
             
-            sampled_target_points_L, sampled_target_normal_L = RenderUtil.get_world_points_and_normal(depth_L,target_mask_img_L,normal_L, cam_info["cam_intrinsic"], cam_info["cam_to_world"],  RenderUtil.random_downsample_N)
+            return filtered_point_cloud, full_scene_point_cloud
-            sampled_target_points_R = RenderUtil.get_world_points(depth_R, target_mask_img_R, cam_info["cam_intrinsic"], cam_info["cam_to_world_R"],  RenderUtil.random_downsample_N  )
-
-
-            has_points = sampled_target_points_L.shape[0] > 0 and sampled_target_points_R.shape[0] > 0
-            if has_points:
-                target_points, overlap_idx = PtsUtil.get_overlapping_points(
-                        sampled_target_points_L, sampled_target_points_R, voxel_threshold, require_idx=True
-                    )
-                sampled_target_normal_L = sampled_target_normal_L[overlap_idx]
-
-            if has_points:
-                has_points = target_points.shape[0] > 0
-
-            if has_points:
-                target_points, target_normals = PtsUtil.filter_points(
-                    target_points, sampled_target_normal_L, cam_info["cam_to_world"], theta_limit = filter_degree, z_range=(RenderUtil.min_z, RenderUtil.max_z)
-                    )
-                
-            
-            scan_points_indices_L = RenderUtil.get_scan_points_indices(scan_points, mask_img_L, RenderUtil.display_table_mask_label, cam_info["cam_intrinsic"], cam_info["cam_to_world"]) 
-            scan_points_indices_R = RenderUtil.get_scan_points_indices(scan_points, mask_img_R, RenderUtil.display_table_mask_label, cam_info["cam_intrinsic"], cam_info["cam_to_world_R"])
-            scan_points_indices = np.intersect1d(scan_points_indices_L, scan_points_indices_R)
-            if not has_points:
-                target_points = np.zeros((0, 3))
-                target_normals = np.zeros((0, 3))
-            end_time = time.time()
-            print(f"-- Time taken for processing: {end_time - start_time} seconds")
-            #import ipdb; ipdb.set_trace()
-            return target_points, target_normals, scan_points_indices