first commit

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

configs/local/global_points_and_pose_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_only"
+  pipeline: nbv_reconstruction_pipeline_global_only
+  voxel_size: 0.003
+  min_new_area: 1.0
+
+dataset:
+    OmniObject3d_test:
+      source: seq_reconstruction_dataset_preprocessed
+      root_dir: /media/hofee/repository/final_test_set/preprocessed_dataset
+      model_dir: /media/hofee/data/data/target/target_formulated_view
+      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

configs/local/global_pts_and_local_pts_pose.yaml

@@ -0,0 +1,117 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: ab_global_pts_and_local_pts_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_pts_pose"
+  pipeline: nbv_reconstruction_pipeline_local
+  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
+    # 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
+
+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: 1280
+    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/local/local_only_inference_config.yaml

@@ -0,0 +1,129 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: ab_local_only
+    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_local_only"
+  pipeline: nbv_reconstruction_pipeline_local_only
+  voxel_size: 0.003
+  min_new_area: 1.0
+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/repository/final_test_set/preprocessed_dataset"
+    model_dir: "/media/hofee/data/data/target/target_formulated_view"
+    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
+
+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: 1280
+    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: 1024
+    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/local/simulation_config.yaml

@@ -0,0 +1,36 @@
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: simulation_debug
+    root_dir: "experiments"
+
+simulation:
+  robot:
+    urdf_path: "assets/franka_panda/panda.urdf"
+    initial_position: [0, 0, 0]  # 机械臂基座位置
+    initial_orientation: [0, 0, 0]  # 机械臂基座朝向(欧拉角)
+  
+  turntable:
+    radius: 0.3  # 转盘半径(米)
+    height: 0.1  # 转盘高度
+    center_position: [0.8, 0, 0.4]  
+  
+  target:
+    obj_dir: /media/hofee/data/project/python/nbv_reconstruction/nbv_reconstruction/assets/object_meshes
+    obj_name: "google_scan-box_0185"        
+    scale: 1.0  # 缩放系数
+    mass: 0.1   # 质量(kg)
+    rgba_color: [0.8, 0.8, 0.8, 1.0]  # 目标物体颜色
+  
+  camera:
+    width: 640
+    height: 480
+    fov: 40
+    near: 0.01
+    far: 5.0
+
+displaytable:

configs/local/split_dataset_config.yaml

@@ -0,0 +1,22 @@
+
+runner:
+  general:
+    seed: 0
+    device: cpu
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: debug
+    root_dir: "experiments"
+  
+  split:
+    root_dir: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/scenes"
+    type: "unseen_instance" # "unseen_category"
+    datasets:
+      OmniObject3d_train: 
+        path: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/OmniObject3d_train.txt"
+        ratio: 0.9
+
+      OmniObject3d_test: 
+        path: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/OmniObject3d_test.txt"
+        ratio: 0.1

configs/local/strategy_generate_config.yaml

@@ -0,0 +1,27 @@
+
+runner:
+  general:
+    seed: 0
+    device: cpu
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+
+    
+  experiment:
+    name: debug
+    root_dir: "experiments"
+      
+  generate:
+    voxel_threshold: 0.003
+    overlap_area_threshold: 30
+    compute_with_normal: False
+    scan_points_threshold: 10
+    overwrite: False  
+    seq_num: 10
+    dataset_list:
+      - OmniObject3d
+  
+datasets:
+    OmniObject3d:
+      root_dir: /media/hofee/data/data/test_bottle/view 
+      from: 0
+      to: -1 # ..-1 means end

configs/local/train_config.yaml

@@ -0,0 +1,105 @@
+
+runner:
+  general:
+    seed: 1
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    parallel: False
+    
+  experiment:
+    name: debug
+    root_dir: "experiments"
+    use_checkpoint: False
+    epoch: 600 # -1 stands for last epoch
+    max_epochs: 5000
+    save_checkpoint_interval: 1
+    test_first: True  
+
+  train:
+    optimizer:
+      type: Adam
+      lr: 0.0001
+    losses: 
+      - gf_loss
+    dataset: OmniObject3d_train
+  test:
+    frequency: 3 # test frequency
+    dataset_list:
+      - OmniObject3d_test
+
+  pipeline: nbv_reconstruction_pipeline
+  
+dataset:
+  OmniObject3d_train:
+    root_dir: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/scenes"
+    model_dir: "/media/hofee/data/data/scaled_object_meshes"
+    source: nbv_reconstruction_dataset
+    split_file: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/OmniObject3d_train.txt"
+    type: train
+    ratio: 1
+    batch_size: 1
+    num_workers: 12
+    pts_num: 4096
+    load_from_preprocess: True
+
+  OmniObject3d_test:
+    root_dir: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/scenes"
+    model_dir: "/media/hofee/data/data/scaled_object_meshes"
+    source: nbv_reconstruction_dataset
+    split_file: "/media/hofee/data/project/python/nbv_reconstruction/sample_for_training/OmniObject3d_train.txt"
+    type: test
+    filter_degree: 75
+    eval_list:
+      - pose_diff
+      - coverage_rate_increase
+    ratio: 0.1
+    batch_size: 1
+    num_workers: 12
+    pts_num: 4096
+    load_from_preprocess: True
+
+pipeline:
+  nbv_reconstruction_pipeline:
+    pts_encoder: pointnet_encoder
+    seq_encoder: transformer_seq_encoder
+    pose_encoder: pose_encoder
+    view_finder: gf_view_finder
+    
+module:
+
+  pointnet_encoder:
+    in_dim: 3
+    out_dim: 1024
+    global_feat: True
+    feature_transform: False
+
+  transformer_seq_encoder:
+    pts_embed_dim: 1024
+    pose_embed_dim: 256
+    num_heads: 4
+    ffn_dim: 256
+    num_layers: 3
+    output_dim: 2048
+
+  gf_view_finder:
+    t_feat_dim: 128
+    pose_feat_dim: 256
+    main_feat_dim: 3072
+    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
+
+loss_function:
+  gf_loss:
+
+evaluation_method:
+  pose_diff:
+  coverage_rate_increase: 
+    renderer_path: "/media/hofee/data/project/python/nbv_reconstruction/blender/data_renderer.py" 

configs/local/uncertainty_guide_evaluation_config.yaml

@@ -0,0 +1,130 @@
+
+runner:
+  general:
+    seed: 0
+    device: cuda
+    cuda_visible_devices: "0,1,2,3,4,5,6,7"
+    
+  experiment:
+    name: uncertainty_guide_evaluation
+    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/old_uncertainty_guide_evaluation"
+  output_data_root: "/media/hofee/repository/code/nbv_rec_uncertainty_guide/output/reconstruction"
+  pipeline: nbv_reconstruction_pipeline_global_only
+  voxel_size: 0.003
+  min_new_area: 1.0
+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
+
+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

configs/local/view_generate_config.yaml

@@ -0,0 +1,52 @@
+runner:
+  general:
+    seed: 0
+    device: cpu
+    cuda_visible_devices: 0,1,2,3,4,5,6,7
+  experiment:
+    name: debug
+    root_dir: experiments
+  generate:
+    port: 5002
+    from: 0
+    to: 50 # -1 means all
+    object_dir: /media/hofee/data/data/test_bottle/bottle_mesh
+    table_model_path: /media/hofee/data/data/others/table.obj
+    output_dir: /media/hofee/data/data/test_bottle/view
+    binocular_vision: true
+    plane_size: 10
+    max_views: 512
+    min_views: 128
+    random_view_ratio: 0.002
+    min_cam_table_included_degree: 20
+    max_diag: 0.7
+    min_diag: 0.01
+    random_config:
+      display_table:
+        min_height: 0.05
+        max_height: 0.15
+        min_radius: 0.2
+        max_radius: 0.3
+      display_object:
+        min_x: 0
+        max_x: 0.05
+        min_y: 0
+        max_y: 0.05
+        min_z: 0.01
+        max_z: 0.01
+        random_rotation_ratio: 0.0
+      random_objects:
+        num: 4
+        cluster: 0.9
+    light_and_camera_config:
+      Camera:
+        near_plane: 0.01
+        far_plane: 5
+        fov_vertical: 25
+        resolution: [640,400]
+        eye_distance: 0.10
+        eye_angle: 25
+      Light:
+        location: [0,0,3.5]
+        orientation: [0,0,0]
+        power: 150