fix overlap bug

app_heuristic.py

@@ -0,0 +1,8 @@
+from PytorchBoot.application import PytorchBootApplication
+from runners.heuristic import Heuristic
+
+@PytorchBootApplication("exp_heuristic")
+class ExpHeuristic:
+    @staticmethod
+    def start():
+        Heuristic("configs/local/heuristic_exp_config.yaml").run()

configs/local/heuristic_exp_config.yaml

@@ -0,0 +1,71 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: exp_hemisphere_circle_trajectory
+    root_dir: "experiments"
+    epoch: -1 # -1 stands for last epoch
+
+  test:
+    dataset_list:
+      - OmniObject3d_test
+
+  blender_script_path: "/media/hofee/data/project/python/nbv_reconstruction/blender/data_renderer.py"
+  output_dir: "/media/hofee/data/results/nbv_rec_inference/hemisphere_random_241202"
+  voxel_size: 0.003
+  min_new_area: 1.0
+  heuristic_method: hemisphere_random
+
+dataset:
+  # OmniObject3d_train:
+  #   root_dir: "C:\\Document\\Datasets\\inference_test1"
+  #   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
+    # split_file: "C:\\Document\\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
+
+heuristic_methods:
+  hemisphere_random:
+    center: [0, 0, 0]
+    radius_fixed: True
+    fixed_radius: 0.6
+    min_radius: 0.4
+    max_radius: 0.8
+
+  hemisphere_circle_trajectory:
+    center: [0, 0, 0]
+    radius_fixed: False
+    fixed_radius: 0.6
+    min_radius: 0.4
+    max_radius: 0.8
+    phi_list: [15, 45, 75]
+    circle_times: 12
+
+
+

configs/local/inference_config.yaml

@@ -6,7 +6,7 @@ runner:
     cuda_visible_devices: "0,1,2,3,4,5,6,7"
     
   experiment:
-    name: train_ab_global_only
+    name: train_ab_partial
     root_dir: "experiments"
     epoch: -1 # -1 stands for last epoch
 
@@ -15,10 +15,10 @@ runner:
       - OmniObject3d_test
 
   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/results/nbv_rec_inference/partial_241202"
   pipeline: nbv_reconstruction_pipeline
   voxel_size: 0.003
-  
+  min_new_area: 1.0
 dataset:
   # OmniObject3d_train:
   #   root_dir: "C:\\Document\\Datasets\\inference_test1"
@@ -66,7 +66,7 @@ module:
     global_feat: True
     feature_transform: False
   transformer_seq_encoder:
-    embed_dim: 256
+    embed_dim: 320
     num_heads: 4
     ffn_dim: 256
     num_layers: 3

configs/local/view_generate_config.yaml

@@ -7,19 +7,17 @@ runner:
     name: debug
     root_dir: experiments
   generate:
-    port: 5000
+    port: 5002
-    from: 0
+    from: 1
-    to: -1 # -1 means all
+    to: 50 # -1 means all
-    object_dir: /media/hofee/data/data/scaled_object_meshes
+    object_dir: C:\\Document\\Datasets\\scaled_object_meshes
-    table_model_path: "/media/hofee/data/data/others/table.obj"
+    table_model_path: C:\\Document\\Datasets\\table.obj
-    output_dir: /media/hofee/data/data/new_testset
+    output_dir: C:\\Document\\Datasets\\debug_generate_view
-    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

core/pipeline.py

@@ -88,26 +88,49 @@ 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_mask_batch = data["scanned_pts_mask"] # List(B): Tensor(S x N)
 
         device = next(self.parameters()).device
 
         embedding_list_batch = []
 
         combined_scanned_pts_batch = data["combined_scanned_pts"]  # Tensor(B x N x 3)
-        global_scanned_feat = self.pts_encoder.encode_points(
+        global_scanned_feat, per_point_feat_batch = self.pts_encoder.encode_points(
-            combined_scanned_pts_batch, require_per_point_feat=False
+            combined_scanned_pts_batch, require_per_point_feat=True
         )  # global_scanned_feat: Tensor(B x Dg)
+        batch_size = len(scanned_n_to_world_pose_9d_batch)
+        for i in range(batch_size):
+            seq_len = len(scanned_n_to_world_pose_9d_batch[i])
+            scanned_n_to_world_pose_9d = scanned_n_to_world_pose_9d_batch[i].to(device)  # Tensor(S x 9)
+            scanned_pts_mask = scanned_pts_mask_batch[i] # Tensor(S x N)
+            per_point_feat = per_point_feat_batch[i] # Tensor(N x Dp)
+            partial_point_feat_seq = []
+            for j in range(seq_len):
+                partial_per_point_feat = per_point_feat[scanned_pts_mask[j]]
+                if partial_per_point_feat.shape[0] == 0:
+                    partial_point_feat = torch.zeros(per_point_feat.shape[1], device=device)
+                else:
+                    partial_point_feat = torch.mean(partial_per_point_feat, dim=0) # Tensor(Dp)
+                partial_point_feat_seq.append(partial_point_feat)
+            partial_point_feat_seq = torch.stack(partial_point_feat_seq, dim=0) # Tensor(S x Dp)
             
-        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)
             pose_feat_seq = self.pose_encoder.encode_pose(scanned_n_to_world_pose_9d)  # Tensor(S x Dp) 
-            seq_embedding = pose_feat_seq
+
+            seq_embedding = torch.cat([partial_point_feat_seq, pose_feat_seq], dim=-1)
+            
             embedding_list_batch.append(seq_embedding) # List(B): Tensor(S x (Dp))
         
         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))
 
         if torch.isnan(main_feat).any():
+            for i in range(len(main_feat)):
+                if torch.isnan(main_feat[i]).any():
+                    scanned_pts_mask = scanned_pts_mask_batch[i]
+                    Log.info(f"scanned_pts_mask shape: {scanned_pts_mask.shape}")
+                    Log.info(f"scanned_pts_mask sum: {scanned_pts_mask.sum()}")
+                    import ipdb
+                    ipdb.set_trace()
             Log.error("nan in main_feat", True)
 
         return main_feat

core/seq_dataset.py

@@ -47,7 +47,8 @@ class SeqReconstructionDataset(BaseDataset):
         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)):
+                if not os.path.exists(os.path.join(self.root_dir, scene_name)):
+                    continue
                 scene_name_list.append(scene_name)
         return scene_name_list
     
@@ -168,7 +169,6 @@ class SeqReconstructionDataset(BaseDataset):
 
 # -------------- Debug ---------------- #
 if __name__ == "__main__":
-    #import ipdb; ipdb.set_trace()
     import torch
     from tqdm import tqdm
     import pickle
@@ -199,6 +199,6 @@ if __name__ == "__main__":
         for key, value in item.items():
             if isinstance(value, np.ndarray):
                 item[key] = value.tolist()
-        import ipdb; ipdb.set_trace()
+        #import ipdb; ipdb.set_trace()
         with open(output_path, "wb") as f:
             pickle.dump(item, f)

core/seq_dataset_preprocessed.py

@@ -15,7 +15,6 @@ 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):
@@ -42,7 +41,6 @@ class SeqReconstructionDatasetPreprocessed(BaseDataset):
     def __len__(self):
         return len(self.item_list)
 
-
 # -------------- Debug ---------------- #
 if __name__ == "__main__":
     import torch

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/heuristic.py

@@ -0,0 +1,425 @@
+import os
+import json
+from utils.render import RenderUtil
+from utils.pose import PoseUtil
+from utils.pts import PtsUtil
+from utils.reconstruction import ReconstructionUtil
+
+import torch
+from tqdm import tqdm
+import numpy as np
+import pickle
+
+from PytorchBoot.config import ConfigManager
+import PytorchBoot.namespace as namespace
+import PytorchBoot.stereotype as stereotype
+from PytorchBoot.factory import ComponentFactory
+
+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("heuristic")
+class Heuristic(Runner):
+    def __init__(self, config_path):
+        
+        super().__init__(config_path)
+    
+        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")
+        self.min_new_area = ConfigManager.get(namespace.Stereotype.RUNNER, "min_new_area")
+        self.heuristic_method = ConfigManager.get(namespace.Stereotype.RUNNER, "heuristic_method")
+        self.heuristic_method_config = ConfigManager.get("heuristic_methods", self.heuristic_method)
+        CM = 0.01
+        self.min_new_pts_num = self.min_new_area * (CM / self.voxel_size) **2
+
+        ''' 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 '''
+        self.test_config = ConfigManager.get(namespace.Stereotype.RUNNER, namespace.Mode.TEST)
+        self.test_dataset_name_list = self.test_config["dataset_list"]
+        self.test_set_list = []
+        self.test_writer_list = []
+        seen_name = set()
+        for test_dataset_name in self.test_dataset_name_list:
+            if test_dataset_name not in seen_name:
+                seen_name.add(test_dataset_name)
+            else:
+                raise ValueError("Duplicate test dataset name: {}".format(test_dataset_name))
+            test_set: BaseDataset = ComponentFactory.create(namespace.Stereotype.DATASET, test_dataset_name)
+            self.test_set_list.append(test_set)
+        self.print_info()
+        
+
+    def run(self):
+        Log.info("Loading from epoch {}.".format(self.current_epoch))
+        self.run_heuristic()
+        Log.success("Inference finished.")
+        
+
+    def run_heuristic(self):
+ 
+        test_set: BaseDataset
+        for dataset_idx, test_set in enumerate(self.test_set_list):
+            status_manager.set_progress("heuristic", "heuristic", f"dataset", dataset_idx, len(self.test_set_list))
+            test_set_name = test_set.get_name()
+
+            total=int(len(test_set))
+            for i in tqdm(range(total), desc=f"Processing {test_set_name}", ncols=100):
+                try:
+                    data = test_set.__getitem__(i)
+                    scene_name = data["scene_name"]
+                    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
+                    
+                    status_manager.set_progress("heuristic", "heuristic", f"Batch[{test_set_name}]", i+1, total)
+                    output = self.predict_sequence(data)
+                    self.save_inference_result(test_set_name, data["scene_name"], output)
+                except Exception as e:
+                    print(e)
+                    Log.error(f"Error, {e}")
+                    continue
+                
+        status_manager.set_progress("heuristic", "heuristic", 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=5000, max_retry=5000, max_success=5000):
+        scene_name = data["scene_name"]
+        Log.info(f"Processing scene: {scene_name}")
+        status_manager.set_status("heuristic", "heuristic", "scene", scene_name)
+
+        ''' data for rendering '''
+        scene_path = data["scene_path"]
+        O_to_L_pose = data["O_to_L_pose"]
+        voxel_threshold = self.voxel_size
+        filter_degree = 75
+        down_sampled_model_pts = data["gt_pts"]
+        
+        first_frame_to_world_9d = data["first_scanned_n_to_world_pose_9d"][0]
+        first_frame_to_world = np.eye(4)
+        first_frame_to_world[:3,:3] = PoseUtil.rotation_6d_to_matrix_numpy(first_frame_to_world_9d[:6])
+        first_frame_to_world[:3,3] = first_frame_to_world_9d[6:]
+        
+        # 获取扫描点
+        root = os.path.dirname(scene_path)
+        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))
+
+        # 生成位姿序列
+        if self.heuristic_method == "hemisphere_random":
+            pose_sequence = self.generate_hemisphere_random_sequence(
+                max_iter,
+                self.heuristic_method_config
+            )
+        elif self.heuristic_method == "hemisphere_circle_trajectory":
+            pose_sequence = self.generate_hemisphere_circle_sequence(
+                self.heuristic_method_config
+            )
+        else:
+            raise ValueError(f"Unknown heuristic method: {self.heuristic_method}")
+
+        # 执行第一帧
+        first_frame_target_pts, _, 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
+        )
+        
+        # 初始化结果存储
+        scanned_view_pts = [first_frame_target_pts]
+        history_indices = [first_frame_scan_points_indices]
+        pred_cr_seq = []
+        retry_duplication_pose = []
+        retry_no_pts_pose = []
+        retry_overlap_pose = []
+        pose_9d_seq = [first_frame_to_world_9d]
+        
+        last_pred_cr, _ = self.compute_coverage_rate(scanned_view_pts, None, down_sampled_model_pts, threshold=voxel_threshold)
+        pred_cr_seq.append(last_pred_cr)
+        last_pts_num = PtsUtil.voxel_downsample_point_cloud(first_frame_target_pts, voxel_threshold).shape[0]
+        
+        # 执行序列
+        retry = 0
+        success = 0
+        #import ipdb; ipdb.set_trace()
+        combined_scanned_pts_tensor = torch.tensor([0,0,0])
+        cnt = 0
+        for pred_pose in pose_sequence:
+            cnt += 1
+            if retry >= max_retry or success >= max_success:
+                break
+            
+            Log.green(f"迭代: {cnt}/{len(pose_sequence)}, 重试: {retry}/{max_retry}, 成功: {success}/{max_success}")
+            
+            try:
+                new_target_pts, _, 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
+                )
+                
+                # 检查扫描点重叠
+                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
+
+                # 检查点云重叠
+                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:
+                    Log.yellow("no overlap!")
+                    retry += 1
+                    retry_overlap_pose.append(pred_pose.tolist())
+                    continue
+
+                if new_target_pts.shape[0] == 0:
+                    Log.red("新视角无点云")
+                    retry_no_pts_pose.append(pred_pose.tolist())
+                    retry += 1
+                    continue
+                    
+                history_indices.append(new_scan_points_indices)
+                
+                # 计算覆盖率
+                pred_cr, _ = self.compute_coverage_rate(scanned_view_pts, new_target_pts, down_sampled_model_pts, threshold=voxel_threshold)
+                Log.yellow(f"覆盖率: {pred_cr}, 上一次: {last_pred_cr}, 最大: {data['seq_max_coverage_rate']}")
+                
+                # 更新结果
+                pred_cr_seq.append(pred_cr)
+                scanned_view_pts.append(new_target_pts)
+                pose_6d = PoseUtil.matrix_to_rotation_6d_numpy(pred_pose[:3,:3])
+                pose_9d = np.concatenate([
+                    pose_6d,
+                    pred_pose[:3,3]
+                ])
+                pose_9d_seq.append(pose_9d)
+                # 处理点云数据用于combined_scanned_pts
+                combined_scanned_pts = np.vstack(scanned_view_pts)
+                voxel_downsampled_pts, _ = self.voxel_downsample_with_mapping(combined_scanned_pts, voxel_threshold)
+                random_downsampled_pts, _ = PtsUtil.random_downsample_point_cloud(voxel_downsampled_pts, 8192, require_idx=True)
+                combined_scanned_pts_tensor = torch.tensor(random_downsampled_pts, dtype=torch.float32)
+
+                
+                # 检查点数增量
+                pts_num = voxel_downsampled_pts.shape[0]
+                Log.info(f"点数增量: {pts_num - last_pts_num}, 当前: {pts_num}, 上一次: {last_pts_num}")
+                
+                if pts_num - last_pts_num < self.min_new_pts_num:
+                    if pred_cr <= data["seq_max_coverage_rate"] - 1e-2:
+                        retry += 1
+                        retry_duplication_pose.append(pred_pose.tolist())
+                        Log.red(f"点数增量过小 < {self.min_new_pts_num}")
+                    else:
+                        success += 1
+                        Log.success(f"达到目标覆盖率")
+                        
+                last_pts_num = pts_num
+                last_pred_cr = pred_cr
+                
+                if pred_cr >= data["seq_max_coverage_rate"] - 1e-3:
+                    Log.success(f"达到最大覆盖率: {pred_cr}")
+                    
+                    
+            except Exception as e:
+                import traceback
+                traceback.print_exc()
+                Log.error(f"场景 {scene_path} 处理出错: {e}")
+                retry_no_pts_pose.append(pred_pose.tolist())
+                retry += 1
+                continue
+
+        # 返回结果
+        result = {
+            "pred_pose_9d_seq": pose_9d_seq,
+            "combined_scanned_pts_tensor": combined_scanned_pts_tensor,
+            "target_pts_seq": scanned_view_pts,
+            "coverage_rate_seq": pred_cr_seq,
+            "max_coverage_rate": data["seq_max_coverage_rate"],
+            "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,
+            "retry_overlap_pose": retry_overlap_pose,
+            "best_seq_len": data["best_seq_len"],
+        }
+        
+        self.stat_result[scene_name] = {
+            "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))
+
+        return result
+
+    def voxel_downsample_with_mapping(self, point_cloud, voxel_size=0.003):
+        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]
+        return downsampled_points, inverse
+    
+    def compute_coverage_rate(self, scanned_view_pts, new_pts, model_pts, threshold=0.005):
+        if new_pts is not None:
+            new_scanned_view_pts = scanned_view_pts + [new_pts]
+        else:
+            new_scanned_view_pts = scanned_view_pts
+        combined_point_cloud = np.vstack(new_scanned_view_pts)
+        down_sampled_combined_point_cloud = PtsUtil.voxel_downsample_point_cloud(combined_point_cloud,threshold)
+        return ReconstructionUtil.compute_coverage_rate(model_pts, down_sampled_combined_point_cloud, threshold)
+        
+
+    def save_inference_result(self, dataset_name, scene_name, output):
+        dataset_dir = os.path.join(self.output_dir, dataset_name)
+        if not os.path.exists(dataset_dir):
+            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:
+            json.dump(self.stat_result, f)
+    
+
+    def get_checkpoint_path(self, is_last=False):
+        return os.path.join(self.experiment_path, namespace.Direcotry.CHECKPOINT_DIR_NAME,
+                            "Epoch_{}.pth".format(
+                                self.current_epoch if self.current_epoch != -1 and not is_last else "last"))
+
+    def load_checkpoint(self, is_last=False):
+        self.load(self.get_checkpoint_path(is_last))
+        Log.success(f"Loaded checkpoint from {self.get_checkpoint_path(is_last)}")
+        if is_last:
+            checkpoint_root = os.path.join(self.experiment_path, namespace.Direcotry.CHECKPOINT_DIR_NAME)
+            meta_path = os.path.join(checkpoint_root, "meta.json")
+            if not os.path.exists(meta_path):
+                raise FileNotFoundError(
+                    "No checkpoint meta.json file in the experiment {}".format(self.experiments_config["name"]))
+            file_path = os.path.join(checkpoint_root, "meta.json")
+            with open(file_path, "r") as f:
+                meta = json.load(f)
+            self.current_epoch = meta["last_epoch"]
+            self.current_iter = meta["last_iter"]
+
+    def load_experiment(self, backup_name=None):
+        super().load_experiment(backup_name)
+        self.current_epoch = self.experiments_config["epoch"]
+
+    def create_experiment(self, backup_name=None):
+        super().create_experiment(backup_name)
+       
+        
+    
+    def print_info(self):
+        def print_dataset(dataset: BaseDataset):
+            config = dataset.get_config()
+            name = dataset.get_name()
+            Log.blue(f"Dataset: {name}")
+            for k,v in config.items():
+                Log.blue(f"\t{k}: {v}")
+
+        super().print_info()
+        table_size = 70
+        Log.blue(f"{'+' + '-' * (table_size // 2)} Datasets {'-' * (table_size // 2)}" + '+')
+        for i, test_set in enumerate(self.test_set_list):
+            Log.blue(f"test dataset {i}: ")
+            print_dataset(test_set)
+
+        Log.blue(f"{'+' + '-' * (table_size // 2)}----------{'-' * (table_size // 2)}" + '+')
+
+    def generate_hemisphere_random_sequence(self, max_iter, config):
+        """Generate a random hemisphere sampling sequence"""
+        radius_fixed = config["radius_fixed"]
+        fixed_radius = config["fixed_radius"]
+        min_radius = config["min_radius"]
+        max_radius = config["max_radius"]
+        poses = []
+        center = np.array(config["center"])
+        
+        for _ in range(max_iter):
+            # 随机采样方向
+            direction = np.random.randn(3)
+            direction[2] = abs(direction[2])  # 确保在上半球
+            direction = direction / np.linalg.norm(direction)
+            
+            # 确定半径
+            if radius_fixed:
+                radius = fixed_radius
+            else:
+                radius = np.random.uniform(min_radius, max_radius)
+                
+            # 计算位置和朝向
+            position = center + direction * radius
+            z_axis = -direction
+            y_axis = np.array([0, 0, 1])
+            x_axis = np.cross(y_axis, z_axis)
+            x_axis = x_axis / np.linalg.norm(x_axis)
+            y_axis = np.cross(z_axis, x_axis)
+            
+            pose = np.eye(4)
+            pose[:3,:3] = np.stack([x_axis, y_axis, z_axis], axis=1)
+            pose[:3,3] = position
+            poses.append(pose)
+            
+        return poses
+
+    def generate_hemisphere_circle_sequence(self, config):
+        """Generate a circular trajectory sampling sequence"""
+        radius_fixed = config["radius_fixed"]
+        fixed_radius = config["fixed_radius"]
+        min_radius = config["min_radius"]
+        max_radius = config["max_radius"]
+        phi_list = config["phi_list"]
+        circle_times = config["circle_times"]
+        
+        poses = []
+        center = np.array(config["center"])
+        
+        for phi in phi_list:  # 仰角
+            phi_rad = np.deg2rad(phi)
+            for i in range(circle_times):  # 方位角
+                theta = i * (2 * np.pi / circle_times)
+                
+                # 确定半径
+                if radius_fixed:
+                    radius = fixed_radius
+                else:
+                    radius = np.random.uniform(min_radius, max_radius)
+                    
+                # 球坐标转笛卡尔坐标
+                x = radius * np.cos(theta) * np.sin(phi_rad)
+                y = radius * np.sin(theta) * np.sin(phi_rad)
+                z = radius * np.cos(phi_rad)
+                position = center + np.array([x, y, z])
+                
+                # 计算朝向
+                direction = (center - position) / np.linalg.norm(center - position)
+                z_axis = direction
+                y_axis = np.array([0, 0, 1])
+                x_axis = np.cross(y_axis, z_axis)
+                x_axis = x_axis / np.linalg.norm(x_axis)
+                y_axis = np.cross(z_axis, x_axis)
+                
+                pose = np.eye(4)
+                pose[:3,:3] = np.stack([x_axis, y_axis, z_axis], axis=1)
+                pose[:3,3] = position
+                poses.append(pose)
+                
+        return poses
+

runners/inference_server.py

@@ -25,6 +25,7 @@ class InferencerServer(Runner):
         self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
         self.pipeline = self.pipeline.to(self.device)
         self.pts_num = 8192
+        self.voxel_size = 0.002
             
         ''' Experiment '''
         self.load_experiment("inferencer_server")
@@ -34,20 +35,14 @@ class InferencerServer(Runner):
         scanned_pts = data["scanned_pts"]
         scanned_n_to_world_pose_9d = data["scanned_n_to_world_pose_9d"]
         combined_scanned_views_pts = np.concatenate(scanned_pts, axis=0)
-        fps_downsampled_combined_scanned_pts, fps_idx = PtsUtil.fps_downsample_point_cloud(
+        voxel_downsampled_combined_scanned_pts = PtsUtil.voxel_downsample_point_cloud(
-            combined_scanned_views_pts, self.pts_num, require_idx=True
+            combined_scanned_views_pts, self.voxel_size
+        )
+        fps_downsampled_combined_scanned_pts, fps_idx = PtsUtil.fps_downsample_point_cloud(
+            voxel_downsampled_combined_scanned_pts, self.pts_num, require_idx=True
         )
-        # combined_scanned_views_pts_mask = np.zeros(len(scanned_pts), dtype=np.uint8)
-        # start_idx = 0
-        # for i in range(len(scanned_pts)):
-        #     end_idx = start_idx + len(scanned_pts[i])
-        #     combined_scanned_views_pts_mask[start_idx:end_idx] = i
-        #     start_idx = end_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_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

runners/inferencer.py

@@ -23,11 +23,15 @@ from utils.data_load import DataLoadUtil
 @stereotype.runner("inferencer")
 class Inferencer(Runner):
     def __init__(self, config_path):
+        
         super().__init__(config_path)
     
         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")
+        self.min_new_area = ConfigManager.get(namespace.Stereotype.RUNNER, "min_new_area")
+        CM = 0.01
+        self.min_new_pts_num = self.min_new_area * (CM / self.voxel_size) **2
         ''' Pipeline '''
         self.pipeline_name = self.config[namespace.Stereotype.PIPELINE]
         self.pipeline:torch.nn.Module = ComponentFactory.create(namespace.Stereotype.PIPELINE, self.pipeline_name)
@@ -74,10 +78,9 @@ class Inferencer(Runner):
 
                 total=int(len(test_set))
                 for i in tqdm(range(total), desc=f"Processing {test_set_name}", ncols=100):
+                    try:
                         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}")
@@ -86,10 +89,14 @@ class Inferencer(Runner):
                         status_manager.set_progress("inference", "inferencer", f"Batch[{test_set_name}]", i+1, total)
                         output = self.predict_sequence(data)
                         self.save_inference_result(test_set_name, data["scene_name"], output)
+                    except Exception as e:
+                        print(e)
+                        Log.error(f"Error, {e}")
+                        continue
                     
             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, overlap_area_threshold=25, scan_points_threshold=10, max_iter=50, max_retry = 10, max_success=3):
         scene_name = data["scene_name"]
         Log.info(f"Processing scene: {scene_name}")
         status_manager.set_status("inference", "inferencer", "scene", scene_name)
@@ -108,13 +115,14 @@ class Inferencer(Runner):
         
         ''' 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_mask"] = [torch.zeros(input_data["combined_scanned_pts"].shape[1], dtype=torch.bool).to(self.device).unsqueeze(0)]
         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["mode"] = namespace.Mode.TEST
         input_pts_N = input_data["combined_scanned_pts"].shape[1]
         
         root = os.path.dirname(scene_path)
-        
         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))
@@ -129,13 +137,13 @@ class Inferencer(Runner):
         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]
+        last_pts_num = PtsUtil.voxel_downsample_point_cloud(data["first_scanned_pts"][0], voxel_threshold).shape[0]
         import time
-        while len(pred_cr_seq) < max_iter and retry < max_retry:
+        while len(pred_cr_seq) < max_iter and retry < max_retry and success < max_success:
-            start_time = time.time()
+            Log.green(f"iter: {len(pred_cr_seq)}, retry: {retry}/{max_retry}, success: {success}/{max_success}")
+            combined_scanned_pts = np.vstack(scanned_view_pts)
+            voxel_downsampled_combined_scanned_pts_np, inverse =  self.voxel_downsample_with_mapping(combined_scanned_pts, voxel_threshold)
             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)
 
@@ -143,7 +151,6 @@ class Inferencer(Runner):
             pred_pose[:3,3] = pred_pose_9d[0,6:]
             
             try:
-                start_time = time.time()
                 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):
@@ -152,17 +159,16 @@ class Inferencer(Runner):
                     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)
+                overlap, _ = ReconstructionUtil.check_overlap(downsampled_new_target_pts, voxel_downsampled_combined_scanned_pts_np, overlap_area_threshold = curr_overlap_area_threshold, voxel_size=voxel_threshold, require_new_added_pts_num = True)
                 if not overlap:
+                    Log.yellow("no 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}")
+                Log.error(f"Error in scene {scene_path}, {e}")
                 print("current pose: ", pred_pose)
                 print("curr_pred_cr: ", last_pred_cr)
                 retry_no_pts_pose.append(pred_pose.cpu().numpy().tolist())
@@ -170,42 +176,94 @@ class Inferencer(Runner):
                 continue
             
             if new_target_pts.shape[0] == 0:
-                print("no pts in new target")
+                Log.red("no pts in new target")
                 retry_no_pts_pose.append(pred_pose.cpu().numpy().tolist())
                 retry += 1
                 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()
+            Log.yellow(f"{pred_cr}, {last_pred_cr}, max: , {data['seq_max_coverage_rate']}")
-            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)
             
             input_data["scanned_n_to_world_pose_9d"] = [torch.cat([input_data["scanned_n_to_world_pose_9d"][0], pred_pose_9d], dim=0)]
-            
+            start_indices = [0]
+            total_points = 0
+            for pts in scanned_view_pts:
+                total_points += pts.shape[0]
+                start_indices.append(total_points)
             combined_scanned_pts = np.vstack(scanned_view_pts)
-            voxel_downsampled_combined_scanned_pts_np = PtsUtil.voxel_downsample_point_cloud(combined_scanned_pts, 0.002)
+            voxel_downsampled_combined_scanned_pts_np, inverse =  self.voxel_downsample_with_mapping(combined_scanned_pts, voxel_threshold)
-            random_downsampled_combined_scanned_pts_np = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, input_pts_N)
+            random_downsampled_combined_scanned_pts_np, random_downsample_idx = PtsUtil.random_downsample_point_cloud(voxel_downsampled_combined_scanned_pts_np, input_pts_N, require_idx=True)
-            input_data["combined_scanned_pts"] = torch.tensor(random_downsampled_combined_scanned_pts_np, dtype=torch.float32).unsqueeze(0).to(self.device)
+            all_idx_unique = np.arange(len(voxel_downsampled_combined_scanned_pts_np))
-
+            all_random_downsample_idx = all_idx_unique[random_downsample_idx]
-            if success > 3:
+            scanned_pts_mask = []
+            for idx, start_idx in enumerate(start_indices):
+                if idx == len(start_indices) - 1:
                     break
+                end_idx = start_indices[idx+1]
+                view_inverse = inverse[start_idx:end_idx]
+                view_unique_downsampled_idx = np.unique(view_inverse)
+                view_unique_downsampled_idx_set = set(view_unique_downsampled_idx)
+                mask = np.array([idx in view_unique_downsampled_idx_set for idx in all_random_downsample_idx])
+                scanned_pts_mask.append(mask)
+
+            input_data["combined_scanned_pts"] = torch.tensor(random_downsampled_combined_scanned_pts_np, dtype=torch.float32).unsqueeze(0).to(self.device)
+            #import ipdb; ipdb.set_trace()
+            input_data["scanned_pts_mask"] = [torch.tensor(scanned_pts_mask, dtype=torch.bool)]
+
+            
             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:
+            Log.info(f"delta pts num:,{pts_num - last_pts_num },{pts_num}, {last_pts_num}")
+
+            if pts_num - last_pts_num < self.min_new_pts_num and pred_cr <= data["seq_max_coverage_rate"] - 1e-2:
                 retry += 1
                 retry_duplication_pose.append(pred_pose.cpu().numpy().tolist())
-                print("delta pts num < 10:", pts_num, last_pts_num)
+                Log.red(f"delta pts num < {self.min_new_pts_num}:, {pts_num}, {last_pts_num}")
+            elif pts_num - last_pts_num < self.min_new_pts_num and pred_cr > data["seq_max_coverage_rate"] - 1e-2:
+                success += 1
+                Log.success(f"delta pts num < {self.min_new_pts_num}:, {pts_num}, {last_pts_num}")
+
             last_pts_num = pts_num
             
+
+        input_data["scanned_n_to_world_pose_9d"] = input_data["scanned_n_to_world_pose_9d"][0].cpu().numpy().tolist()
+        result = {
+            "pred_pose_9d_seq": input_data["scanned_n_to_world_pose_9d"],
+            "combined_scanned_pts": input_data["combined_scanned_pts"],
+            "target_pts_seq": scanned_view_pts,
+            "coverage_rate_seq": pred_cr_seq,
+            "max_coverage_rate": data["seq_max_coverage_rate"],
+            "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,
+            "retry_overlap_pose": retry_overlap_pose,
+            "best_seq_len": data["best_seq_len"],
+        }
+        self.stat_result[scene_name] = {
+            "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))
+
+        return result
+
+    def voxel_downsample_with_mapping(self, point_cloud, voxel_size=0.003):
+        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]
+        return downsampled_points, inverse
+    
     def compute_coverage_rate(self, scanned_view_pts, new_pts, model_pts, threshold=0.005):
         if new_pts is not None:
             new_scanned_view_pts = scanned_view_pts + [new_pts]

runners/view_generator.py

@@ -9,7 +9,7 @@ class ViewGenerator(Runner):
         self.config_path = config_path
         
     def run(self):
-        result = subprocess.run(['/home/hofee/blender-4.0.2-linux-x64/blender', '-b', '-P', '../blender/run_blender.py', '--', self.config_path])
+        result = subprocess.run(['blender', '-b', '-P', '../blender/run_blender.py', '--', self.config_path])
         print()
 
     def create_experiment(self, backup_name=None):

utils/render.py

@@ -84,13 +84,10 @@ 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
             ], capture_output=True, text=True)
-            end_time = time.time()
+            # print(result)
-
-            print(f"-- Time taken for blender: {end_time - start_time} seconds")
             path = os.path.join(temp_dir, "tmp")
             cam_info = DataLoadUtil.load_cam_info(path, binocular=True)
             depth_L, depth_R = DataLoadUtil.load_depth(
@@ -98,7 +95,6 @@ class RenderUtil:
                     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 '''
@@ -135,7 +131,5 @@ class RenderUtil:
             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

utils/vis.py

@@ -175,6 +175,9 @@ class visualizeUtil:
         np.savetxt(os.path.join(output_dir, "nrm.txt"), visualized_nrm)
         np.savetxt(os.path.join(output_dir, "pts.txt"), pts_world)
     
+    # @staticmethod
+    # def save_
+        
 # ------ Debug ------
 
 if __name__ == "__main__":