first commit

2025-05-13 09:03:38 +08:00
commit b98753bfbb
121 changed files with 8665 additions and 0 deletions
--- a/configs/local/global_only_inference_config.yaml
+++ b/configs/local/global_only_inference_config.yaml
@@ -0,0 +1,115 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: ab_global_pts_and_local_pose
+    root_dir: "experiments"
+    epoch: 200 # -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/project/exp/new_ab_global_pts_and_local_pose"
+  pipeline: nbv_reconstruction_pipeline_global
+  voxel_size: 0.003
+  min_new_area: 1.0
+dataset:
+  OmniObject3d_test:
+    root_dir: "/media/hofee/repository/final_test_set/preprocessed_dataset"
+    model_dir: "/media/hofee/data/data/target/target_formulated_view"
+    source: seq_reconstruction_dataset_preprocessed
+    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
+
+pipeline:
+  nbv_reconstruction_pipeline_local:
+    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
+  nbv_reconstruction_pipeline_global:
+    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
+  nbv_reconstruction_pipeline_local_only:
+    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
+  nbv_reconstruction_pipeline_global_only:
+    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
+  nbv_reconstruction_pipeline_mlp:
+    modules:
+      pts_encoder: pointnet++_encoder
+      seq_encoder: transformer_seq_encoder
+      pose_encoder: pose_encoder
+      view_finder: mlp_view_finder
+    eps: 1e-5
+    global_scanned_feat: True
+
+    
+module:
+
+  pointnet_encoder:
+    in_dim: 3
+    out_dim: 1024
+    global_feat: True
+    feature_transform: False
+
+  pointnet++_encoder:
+    in_dim: 3
+
+  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