upd

configs/local/inference_config.yaml

@@ -14,30 +14,30 @@ runner:
     dataset_list:
       - OmniObject3d_test
 
-  blender_script_path: "/data/hofee/project/nbv_rec/blender/data_renderer.py"
+  blender_script_path: "/media/hofee/data/project/python/nbv_reconstruction/blender/data_renderer.py"
-  output_dir: "/data/hofee/data/inference_global_full_on_testset"
+  output_dir: "/media/hofee/data/data/new_inference_test_output"
   pipeline: nbv_reconstruction_pipeline
   voxel_size: 0.003
-  
+  min_new_area: 1.0
 dataset:
-  OmniObject3d_train:
+  # OmniObject3d_train:
-    root_dir: "/data/hofee/data/new_full_data"
+  #   root_dir: "C:\\Document\\Datasets\\inference_test1"
-    model_dir: "/data/hofee/data/scaled_object_meshes"
+  #   model_dir: "C:\\Document\\Datasets\\scaled_object_meshes"
-    source: seq_reconstruction_dataset
+  #   source: seq_reconstruction_dataset_preprocessed
-    split_file: "/data/hofee/data/sample.txt"
+  #   split_file: "C:\\Document\\Datasets\\data_list\\sample.txt"
-    type: test
+  #   type: test
-    filter_degree: 75
+  #   filter_degree: 75
-    ratio: 1
+  #   ratio: 1
-    batch_size: 1
+  #   batch_size: 1
-    num_workers: 12
+  #   num_workers: 12
-    pts_num: 8192
+  #   pts_num: 8192
-    load_from_preprocess: True
+  #   load_from_preprocess: True
 
   OmniObject3d_test:
-    root_dir: "/data/hofee/data/new_full_data"
+    root_dir: "/media/hofee/data/data/new_testset_output"
-    model_dir: "/data/hofee/data/scaled_object_meshes"
+    model_dir: "/media/hofee/data/data/scaled_object_meshes"
-    source: seq_reconstruction_dataset
+    source: seq_reconstruction_dataset_preprocessed
-    split_file: "/data/hofee/data/new_full_data_list/OmniObject3d_test.txt"
+    # split_file: "C:\\Document\\Datasets\\data_list\\OmniObject3d_test.txt"
     type: test
     filter_degree: 75
     eval_list:

configs/local/view_generate_config.yaml

@@ -8,11 +8,11 @@ runner:
     root_dir: experiments
   generate:
     port: 5002
-    from: 600
+    from: 1
-    to: -1 # -1 means all
+    to: 50 # -1 means all
-    object_dir: /media/hofee/data/data/object_meshes_part1
+    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/repository/data_part_1
+    output_dir: C:\\Document\\Datasets\\debug_generate_view
     binocular_vision: true
     plane_size: 10
     max_views: 512

core/seq_dataset.py

@@ -8,7 +8,7 @@ import torch
 import os
 import sys
 
-sys.path.append(r"/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
@@ -47,6 +47,8 @@ class SeqReconstructionDataset(BaseDataset):
         with open(self.split_file_path, "r") as f:
             for line in f:
                 scene_name = line.strip()
+                if not os.path.exists(os.path.join(self.root_dir, scene_name)):
+                    continue
                 scene_name_list.append(scene_name)
         return scene_name_list    
     
@@ -59,29 +61,19 @@ class SeqReconstructionDataset(BaseDataset):
         total = len(self.scene_name_list)
         for idx, scene_name in enumerate(self.scene_name_list):
             print(f"processing {scene_name} ({idx}/{total})")
-            seq_num = DataLoadUtil.get_label_num(self.root_dir, scene_name)
-            scene_max_coverage_rate = 0
-            max_coverage_rate_list = []
             scene_max_cr_idx = 0
-            for seq_idx in range(seq_num):
+            frame_len = DataLoadUtil.get_scene_seq_length(self.root_dir, scene_name)
-                label_path = DataLoadUtil.get_label_path(
+
-                    self.root_dir, scene_name, seq_idx
+            for i in range(frame_len):
-                )
+                path = DataLoadUtil.get_path(self.root_dir, scene_name, i)
-                label_data = DataLoadUtil.load_label(label_path)
+                pts = DataLoadUtil.load_from_preprocessed_pts(path, "npy")
-                max_coverage_rate = label_data["max_coverage_rate"]
+                if pts.shape[0] == 0:
-                if max_coverage_rate > scene_max_coverage_rate:
+                    continue
-                    scene_max_coverage_rate = max_coverage_rate
-                    scene_max_cr_idx = seq_idx
-                max_coverage_rate_list.append(max_coverage_rate)
-            best_label_path = DataLoadUtil.get_label_path(self.root_dir, scene_name, scene_max_cr_idx)
-            best_label_data = DataLoadUtil.load_label(best_label_path)
-            first_frame = best_label_data["best_sequence"][0]
-            best_seq_len = len(best_label_data["best_sequence"])
             datalist.append({
                 "scene_name": scene_name,
-                "first_frame": first_frame,
+                "first_frame": i,
-                "best_seq_len": best_seq_len,
+                "best_seq_len": -1,
-                "max_coverage_rate": scene_max_coverage_rate,
+                "max_coverage_rate": 1.0,
                 "label_idx": scene_max_cr_idx,
             })  
         return datalist
@@ -132,8 +124,7 @@ class SeqReconstructionDataset(BaseDataset):
             scanned_n_to_world_pose,
         ) = ([], [], [])
         view = data_item_info["first_frame"]
-        frame_idx = view[0]
+        frame_idx = view
-        coverage_rate = view[1]
         view_path = DataLoadUtil.get_path(self.root_dir, scene_name, frame_idx)
         cam_info = DataLoadUtil.load_cam_info(view_path, binocular=True)
         
@@ -145,7 +136,7 @@ class SeqReconstructionDataset(BaseDataset):
             target_point_cloud, self.pts_num
         )
         scanned_views_pts.append(downsampled_target_point_cloud)
-        scanned_coverages_rate.append(coverage_rate)
+        
         n_to_world_6d = PoseUtil.matrix_to_rotation_6d_numpy(
             np.asarray(n_to_world_pose[:3, :3])
         ) 
@@ -162,7 +153,6 @@ class SeqReconstructionDataset(BaseDataset):
         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_scanned_coverage_rate": scanned_coverages_rate, # List(S): Float, range(0, 1)
             "first_scanned_n_to_world_pose_9d": np.asarray(scanned_n_to_world_pose, dtype=np.float32), # Ndarray(S x 9)
             "seq_max_coverage_rate": max_coverage_rate, # Float, range(0, 1)
             "best_seq_len": best_seq_len, # Int
@@ -190,9 +180,9 @@ if __name__ == "__main__":
     np.random.seed(seed)
     
     config = {
-        "root_dir": "/data/hofee/data/new_full_data",
+        "root_dir": "/media/hofee/data/data/new_testset",
         "source": "seq_reconstruction_dataset",
-        "split_file": "/data/hofee/data/new_full_data_list/OmniObject3d_test.txt",
+        "split_file": "/media/hofee/data/data/OmniObject3d_test.txt",
         "load_from_preprocess": True,
         "filter_degree": 75,
         "num_workers": 0,
@@ -200,22 +190,16 @@ if __name__ == "__main__":
         "type": namespace.Mode.TEST,
     }
     
-    output_dir = "/data/hofee/trash_can/output_inference_test"
+    output_dir = "/media/hofee/data/data/new_testset_output"
-    new_output_dir = "/data/hofee/inference_test"
     os.makedirs(output_dir, exist_ok=True)
-    os.makedirs(new_output_dir, exist_ok=True)
 
     ds = SeqReconstructionDataset(config)
     for i in tqdm(range(len(ds)), desc="processing dataset"):
         output_path = os.path.join(output_dir, f"item_{i}.pkl")
-        if os.path.exists(output_path):
-            item = pickle.load(open(output_path, "rb"))
-        else:
         item = ds.__getitem__(i)
         for key, value in item.items():
             if isinstance(value, np.ndarray):
                 item[key] = value.tolist()
-        new_output_path = os.path.join(new_output_dir, f"item_{i}.pkl")
+        #import ipdb; ipdb.set_trace()
-        with open(new_output_path, "wb") as f:
+        with open(output_path, "wb") as f:
             pickle.dump(item, f)
-

core/seq_dataset_preprocessed.py

@@ -0,0 +1,82 @@
+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))
+    

runners/inference_server.py

@@ -41,17 +41,8 @@ class InferencerServer(Runner):
         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

@@ -19,15 +19,19 @@ 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):
+        
         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)
@@ -35,6 +39,11 @@ 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 '''
@@ -68,22 +77,25 @@ class Inferencer(Runner):
                 test_set_name = test_set.get_name()
 
                 total=int(len(test_set))
-                scene_name_list = test_set.get_scene_name_list()
+                for i in tqdm(range(total), desc=f"Processing {test_set_name}", ncols=100):
-                for i in range(total):
+                    try:
-                    scene_name = scene_name_list[i]
+                        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
-                    data = test_set.__getitem__(i)
+                        
                         status_manager.set_progress("inference", "inferencer", f"Batch[{test_set_name}]", i+1, total)
-                    scene_name = data["scene_name"]
                         output = self.predict_sequence(data)
                         self.save_inference_result(test_set_name, data["scene_name"], output)
+                    except Exception as e:
+                        Log.error(f"Error in scene {scene_name}, {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, 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)
@@ -106,21 +118,27 @@ class Inferencer(Runner):
         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]
-        first_frame_target_pts, first_frame_target_normals = RenderUtil.render_pts(first_frame_to_world, scene_path, self.script_path, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
-        scanned_view_pts = [first_frame_target_pts]
-        last_pred_cr, added_pts_num = self.compute_coverage_rate(scanned_view_pts, None, down_sampled_model_pts, threshold=voxel_threshold)
         
+        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))
+
+        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, 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], 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}")
             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)
 
@@ -128,12 +146,24 @@ 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)
-                new_target_pts, new_target_normals = RenderUtil.render_pts(pred_pose, scene_path, self.script_path, voxel_threshold=voxel_threshold, filter_degree=filter_degree, nO_to_nL_pose=O_to_L_pose)
+                #import ipdb; ipdb.set_trace()
-                end_time = time.time()
+                if not ReconstructionUtil.check_scan_points_overlap(history_indices, new_scan_points_indices, scan_points_threshold):
-                print(f"Time taken for rendering: {end_time - start_time} seconds")
+                    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:
+                    Log.yellow("no overlap!")
+                    retry += 1
+                    retry_overlap_pose.append(pred_pose.cpu().numpy().tolist())
+                    continue
+                
+                history_indices.append(new_scan_points_indices)
             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())
@@ -141,42 +171,43 @@ 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)
-            pred_cr, new_added_pts_num = self.compute_coverage_rate(scanned_view_pts, new_target_pts, down_sampled_model_pts, threshold=voxel_threshold)
+            Log.yellow(f"{pred_cr}, {last_pred_cr}, max: , {data['seq_max_coverage_rate']}")
-            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
-            elif new_added_pts_num < 10:
-                print("min added pts num reached!: ", new_added_pts_num)
-            if pred_cr <= last_pred_cr + cr_increase_threshold:
-                retry += 1
-                retry_duplication_pose.append(pred_pose.cpu().numpy().tolist())
-                continue
                 
-            retry = 0
+        
+
             pred_cr_seq.append(pred_cr)
             scanned_view_pts.append(new_target_pts)
-            down_sampled_new_pts_world = PtsUtil.random_downsample_point_cloud(new_target_pts, input_pts_N)
             
-            new_pts = down_sampled_new_pts_world
             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_pts = np.concatenate([input_data["combined_scanned_pts"][0].cpu().numpy(), new_pts], axis=0)
+            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 = PtsUtil.voxel_downsample_point_cloud(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)
             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]
+            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())
+                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 = {
@@ -189,6 +220,7 @@ class Inferencer(Runner):
             "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] = {
@@ -216,7 +248,7 @@ 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(os.path.join(dataset_dir, "stat.json"), "w") as f:
+        with open(self.stat_result_path, "w") as f:
             json.dump(self.stat_result, f)
     
 

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/reconstruction.py

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

@@ -54,7 +54,22 @@ class RenderUtil:
         return points_camera_world
     
     @staticmethod
-    def render_pts(cam_pose, scene_path, script_path, voxel_threshold=0.005, filter_degree=75, nO_to_nL_pose=None, require_full_scene=False):
+    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)
 
@@ -69,17 +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([
-                'blender', '-b', '-P', script_path, '--', temp_dir
+                '/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(result)
-            print(f"-- Time taken for blender: {end_time - start_time} seconds")
-            if result.returncode != 0:
-                print("Blender script failed:")
-                print(result.stderr)
-                return None
             path = os.path.join(temp_dir, "tmp")
             cam_info = DataLoadUtil.load_cam_info(path, binocular=True)
             depth_L, depth_R = DataLoadUtil.load_depth(
@@ -87,7 +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 '''
@@ -117,10 +124,12 @@ class RenderUtil:
                     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
+            return target_points, target_normals, scan_points_indices