update normal strategy

app_generate_strategy.py

@@ -5,5 +5,5 @@ from runners.strategy_generator import StrategyGenerator
 class DataGenerateApp:
     @staticmethod
     def start():
-        StrategyGenerator("configs/server/server_strategy_generate_config.yaml").run()
+        StrategyGenerator("configs/local/strategy_generate_config.yaml").run()
         

configs/local/strategy_generate_config.yaml

@@ -12,8 +12,9 @@ runner:
       
   generate:
     voxel_threshold: 0.003
-    soft_overlap_threshold: 0.3
+    overlap_area_threshold: 25
-    hard_overlap_threshold: 0.6
+    compute_with_normal: True
+    scan_points_threshold: 10
     overwrite: False
     seq_num: 15
     dataset_list:
@@ -21,8 +22,8 @@ runner:
   
 datasets:
     OmniObject3d:
-      root_dir: /media/hofee/repository/full_data_output 
+      root_dir: C:\\Document\\Local Project\\nbv_rec\\nbv_reconstruction\\temp
       from: 0
-      to: -1 # -1 means end
+      to: 1 # -1 means end
 
     

configs/local/view_generate_config.yaml

@@ -7,21 +7,12 @@ runner:
     name: debug
     root_dir: experiments
   generate:
-<<<<<<< HEAD
     port: 5002
     from: 600
     to: -1 # -1 means all
     object_dir: /media/hofee/data/data/object_meshes_part1
     table_model_path: "/media/hofee/data/data/others/table.obj"
     output_dir: /media/hofee/repository/data_part_1
-=======
-    port: 5000
-    from: 0
-    to: -1 # -1 means all
-    object_dir: H:\\AI\\Datasets\\object_meshes_part2
-    table_model_path: "H:\\AI\\Datasets\\table.obj"
-    output_dir: C:\\Document\\Datasets\\nbv_rec_part2
->>>>>>> c55a398b6d5c347497b528bdd460e26ffdd184e8
     binocular_vision: true
     plane_size: 10
     max_views: 512

preprocess/preprocessor.py

@@ -163,16 +163,10 @@ 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 = r"/media/hofee/repository/data_part_1"
+    root = r"C:\Document\Local Project\nbv_rec\nbv_reconstruction\temp"
-    # list_path = r"/media/hofee/repository/full_list.txt"
-    # scene_list = []
-    
-    # with open(list_path, "r") as f:
-    #     for line in f:
-    #         scene_list.append(line.strip())
     scene_list = os.listdir(root)
     from_idx = 0 # 1000
-    to_idx = 600 # 1500
+    to_idx = len(scene_list) # 1500
 
 
     cnt = 0

runners/strategy_generator.py

@@ -24,12 +24,15 @@ class StrategyGenerator(Runner):
         }
         self.overwrite = ConfigManager.get("runner", "generate", "overwrite")
         self.seq_num = ConfigManager.get("runner","generate","seq_num")
+        self.overlap_area_threshold = ConfigManager.get("runner","generate","overlap_area_threshold")
+        self.compute_with_normal = ConfigManager.get("runner","generate","compute_with_normal")
+        self.scan_points_threshold = ConfigManager.get("runner","generate","scan_points_threshold")
         
 
         
     def run(self):
         dataset_name_list =  ConfigManager.get("runner", "generate", "dataset_list")
-        voxel_threshold, soft_overlap_threshold, hard_overlap_threshold = ConfigManager.get("runner","generate","voxel_threshold"), ConfigManager.get("runner","generate","soft_overlap_threshold"), ConfigManager.get("runner","generate","hard_overlap_threshold")
+        voxel_threshold = ConfigManager.get("runner","generate","voxel_threshold")
         for dataset_idx in range(len(dataset_name_list)):
             dataset_name = dataset_name_list[dataset_idx]
             status_manager.set_progress("generate_strategy", "strategy_generator", "dataset", dataset_idx, len(dataset_name_list))
@@ -51,7 +54,7 @@ class StrategyGenerator(Runner):
                     cnt += 1
                     continue
                 
-                self.generate_sequence(root_dir, scene_name,voxel_threshold, soft_overlap_threshold, hard_overlap_threshold)
+                self.generate_sequence(root_dir, scene_name,voxel_threshold)
                 cnt += 1
             status_manager.set_progress("generate_strategy", "strategy_generator", "scene", total, total)
         status_manager.set_progress("generate_strategy", "strategy_generator", "dataset", len(dataset_name_list), len(dataset_name_list))
@@ -64,28 +67,34 @@ class StrategyGenerator(Runner):
     def load_experiment(self, backup_name=None):
         super().load_experiment(backup_name)
     
-    def generate_sequence(self, root, scene_name, voxel_threshold, soft_overlap_threshold, hard_overlap_threshold):
+    def generate_sequence(self, root, scene_name, voxel_threshold):
         status_manager.set_status("generate_strategy", "strategy_generator", "scene", scene_name)
         frame_num = DataLoadUtil.get_scene_seq_length(root, scene_name)
         
         model_points_normals = DataLoadUtil.load_points_normals(root, scene_name)
         model_pts = model_points_normals[:,:3]
-        down_sampled_model_pts = PtsUtil.voxel_downsample_point_cloud(model_pts, voxel_threshold)
+        down_sampled_model_pts, idx = PtsUtil.voxel_downsample_point_cloud(model_pts, voxel_threshold, require_idx=True)
+        down_sampled_model_nrm = model_points_normals[idx, 3:]
         pts_list = []
+        nrm_list = []
         scan_points_indices_list = []
         non_zero_cnt = 0
 
         for frame_idx in range(frame_num):
             status_manager.set_progress("generate_strategy", "strategy_generator", "loading frame", frame_idx, frame_num)
             pts_path = os.path.join(root,scene_name, "pts", f"{frame_idx}.npy")
+            nrm_path = os.path.join(root,scene_name, "nrm", f"{frame_idx}.npy")
             idx_path = os.path.join(root,scene_name, "scan_points_indices", f"{frame_idx}.npy")
-            point_cloud = np.load(pts_path)
+            pts = np.load(pts_path)
-            sampled_point_cloud = PtsUtil.voxel_downsample_point_cloud(point_cloud, voxel_threshold)
+            if pts.shape[0] == 0:
+                nrm = np.zeros((0,3))
+            else:
+                nrm = np.load(nrm_path)
             indices = np.load(idx_path) 
-            pts_list.append(sampled_point_cloud)
+            pts_list.append(pts)
-            
+            nrm_list.append(nrm)
             scan_points_indices_list.append(indices)
-            if sampled_point_cloud.shape[0] > 0:
+            if pts.shape[0] > 0:
                 non_zero_cnt += 1
         status_manager.set_progress("generate_strategy", "strategy_generator", "loading frame", frame_num, frame_num)
         
@@ -93,7 +102,7 @@ class StrategyGenerator(Runner):
         init_view_list = []
         idx = 0
         while len(init_view_list) < seq_num and idx < len(pts_list):
-            if pts_list[idx].shape[0] > 100:
+            if pts_list[idx].shape[0] > 50:
                 init_view_list.append(idx)
             idx += 1
 
@@ -102,8 +111,13 @@ class StrategyGenerator(Runner):
         for init_view in init_view_list:
             status_manager.set_progress("generate_strategy", "strategy_generator", "computing sequence", seq_idx, len(init_view_list))
             start = time.time()
-            limited_useful_view, _, _ = ReconstructionUtil.compute_next_best_view_sequence_with_overlap(down_sampled_model_pts, pts_list, scan_points_indices_list = scan_points_indices_list,init_view=init_view, 
+
-                                                                                                        threshold=voxel_threshold, soft_overlap_threshold=soft_overlap_threshold, hard_overlap_threshold= hard_overlap_threshold, scan_points_threshold=10, status_info=self.status_info)
+            if not self.compute_with_normal:    
+                limited_useful_view, _, _ = ReconstructionUtil.compute_next_best_view_sequence(down_sampled_model_pts, pts_list, scan_points_indices_list = scan_points_indices_list,init_view=init_view, 
+                                                                                                            threshold=voxel_threshold, scan_points_threshold=self.scan_points_threshold, overlap_area_threshold=self.overlap_area_threshold, status_info=self.status_info)
+            else:
+                limited_useful_view, _, _ = ReconstructionUtil.compute_next_best_view_sequence_with_normal(down_sampled_model_pts, down_sampled_model_nrm, pts_list, nrm_list, scan_points_indices_list = scan_points_indices_list,init_view=init_view, 
+                                                                                                            threshold=voxel_threshold, scan_points_threshold=self.scan_points_threshold, overlap_area_threshold=self.overlap_area_threshold, status_info=self.status_info)
             end = time.time()
             print(f"Time: {end-start}")
             data_pairs = self.generate_data_pairs(limited_useful_view)

utils/pts.py

@@ -5,7 +5,7 @@ import torch
 class PtsUtil:
 
     @staticmethod
-    def voxel_downsample_point_cloud(point_cloud, voxel_size=0.005):
+    def voxel_downsample_point_cloud(point_cloud, voxel_size=0.005, require_idx=False):
         voxel_indices = np.floor(point_cloud / voxel_size).astype(np.int32)
         unique_voxels = np.unique(voxel_indices, axis=0, return_inverse=True)
         return unique_voxels[0]*voxel_size

utils/reconstruction.py

@@ -8,14 +8,15 @@ class ReconstructionUtil:
     def compute_coverage_rate(target_point_cloud, combined_point_cloud, threshold=0.01):
         kdtree = cKDTree(combined_point_cloud)
         distances, _ = kdtree.query(target_point_cloud)
-        covered_points_num = np.sum(distances < threshold)
+        covered_points_num = np.sum(distances < threshold*2)
         coverage_rate = covered_points_num / target_point_cloud.shape[0]
         return coverage_rate, covered_points_num
     
+    @staticmethod
     def compute_coverage_rate_with_normal(target_point_cloud, combined_point_cloud, target_normal, combined_normal, threshold=0.01, normal_threshold=0.1):
         kdtree = cKDTree(combined_point_cloud)
         distances, indices = kdtree.query(target_point_cloud)
-        is_covered_by_distance = distances < threshold
+        is_covered_by_distance = distances < threshold*2
         normal_dots = np.einsum('ij,ij->i', target_normal, combined_normal[indices])
         is_covered_by_normal = normal_dots > normal_threshold
         covered_points_num = np.sum(is_covered_by_distance & is_covered_by_normal)
@@ -25,15 +26,14 @@ class ReconstructionUtil:
         
     
     @staticmethod
-    def compute_overlap_rate(new_point_cloud, combined_point_cloud, threshold=0.01):
+    def check_overlap(new_point_cloud, combined_point_cloud, overlap_area_threshold=25, voxel_size=0.01):
         kdtree = cKDTree(combined_point_cloud)
         distances, _ = kdtree.query(new_point_cloud)
-        overlapping_points = np.sum(distances < threshold)
+        overlapping_points = np.sum(distances < voxel_size*2)
-        if new_point_cloud.shape[0] == 0:
+        cm = 0.01
-            overlap_rate = 0
+        voxel_size_cm = voxel_size / cm
-        else:
+        overlap_area = overlapping_points * voxel_size_cm * voxel_size_cm
-            overlap_rate = overlapping_points / new_point_cloud.shape[0]
+        return overlap_area > overlap_area_threshold
-        return overlap_rate
 
 
     @staticmethod
@@ -49,7 +49,7 @@ class ReconstructionUtil:
         return new_added_points
     
     @staticmethod
-    def compute_next_best_view_sequence_with_overlap(target_point_cloud, point_cloud_list, scan_points_indices_list, threshold=0.01, soft_overlap_threshold=0.5, hard_overlap_threshold=0.7, init_view = 0, scan_points_threshold=5, status_info=None):
+    def compute_next_best_view_sequence(target_point_cloud, point_cloud_list, scan_points_indices_list, threshold=0.01, overlap_area_threshold=25, init_view = 0, scan_points_threshold=5, status_info=None):
         selected_views = [init_view]
         combined_point_cloud = point_cloud_list[init_view]
         history_indices = [scan_points_indices_list[init_view]]
@@ -83,22 +83,16 @@ class ReconstructionUtil:
                 if selected_views:
                     new_scan_points_indices = scan_points_indices_list[view_index]
                     if not ReconstructionUtil.check_scan_points_overlap(history_indices, new_scan_points_indices, scan_points_threshold):
-                        overlap_threshold = hard_overlap_threshold
+                        curr_overlap_area_threshold = overlap_area_threshold
                     else:
-                        overlap_threshold = soft_overlap_threshold
+                        curr_overlap_area_threshold = overlap_area_threshold * 0.5
-                    start = time.time()
+                        
-                    overlap_rate = ReconstructionUtil.compute_overlap_rate(point_cloud_list[view_index],combined_point_cloud, threshold)
+                    if not ReconstructionUtil.check_overlap(point_cloud_list[view_index], combined_point_cloud, overlap_area_threshold = curr_overlap_area_threshold, voxel_size=threshold):
-                    end = time.time()
-                    # print(f"overlap_rate Time: {end-start}")
-                    if overlap_rate < overlap_threshold:
                         continue
                 
-                start = time.time()
                 new_combined_point_cloud = np.vstack([combined_point_cloud, point_cloud_list[view_index]])
                 new_downsampled_combined_point_cloud = PtsUtil.voxel_downsample_point_cloud(new_combined_point_cloud,threshold)
                 new_coverage, new_covered_num = ReconstructionUtil.compute_coverage_rate(downsampled_max_rec_pts, new_downsampled_combined_point_cloud, threshold)
-                end = time.time()   
-                #print(f"compute_coverage_rate Time: {end-start}")
                 coverage_increase = new_coverage - current_coverage
                 if coverage_increase > best_coverage_increase:
                     best_coverage_increase = coverage_increase
@@ -107,6 +101,101 @@ class ReconstructionUtil:
                     best_combined_point_cloud = new_downsampled_combined_point_cloud
                     
             
+            if best_view is not None:
+                if best_coverage_increase <=1e-3 or best_covered_num - current_covered_num <= 5:
+                    break
+                
+                selected_views.append(best_view)
+                best_rec_pts_num = best_combined_point_cloud.shape[0]
+                print(f"Current rec pts num: {curr_rec_pts_num}, Best rec pts num: {best_rec_pts_num}, Best cover pts: {best_covered_num}, Max rec pts num: {max_rec_pts_num}")
+                print(f"Current coverage: {current_coverage+best_coverage_increase}, Best coverage increase: {best_coverage_increase}, Max Real coverage: {max_real_rec_pts_coverage}")
+                current_covered_num = best_covered_num
+                curr_rec_pts_num = best_rec_pts_num
+                combined_point_cloud = best_combined_point_cloud
+                remaining_views.remove(best_view)
+                history_indices.append(scan_points_indices_list[best_view])
+                current_coverage += best_coverage_increase
+                cnt_processed_view += 1
+                if status_info is not None:
+                    sm = status_info["status_manager"]
+                    app_name = status_info["app_name"]
+                    runner_name = status_info["runner_name"]
+                    sm.set_status(app_name, runner_name, "current coverage", current_coverage)
+                    sm.set_progress(app_name, runner_name, "processed view", cnt_processed_view, len(point_cloud_list))
+            
+                view_sequence.append((best_view, current_coverage))
+                
+            else:
+                break
+        if status_info is not None:
+            sm = status_info["status_manager"]
+            app_name = status_info["app_name"]
+            runner_name = status_info["runner_name"]
+            sm.set_progress(app_name, runner_name, "processed view", len(point_cloud_list), len(point_cloud_list))
+        return view_sequence, remaining_views, combined_point_cloud
+    
+    @staticmethod
+    def compute_next_best_view_sequence_with_normal(target_point_cloud, target_normal, point_cloud_list, normal_list, scan_points_indices_list, threshold=0.01, overlap_area_threshold=25, init_view = 0, scan_points_threshold=5, status_info=None):
+        selected_views = [init_view]
+        combined_point_cloud = point_cloud_list[init_view]
+        combined_normal = normal_list[init_view]
+        history_indices = [scan_points_indices_list[init_view]]
+        
+        max_rec_pts = np.vstack(point_cloud_list)
+        max_rec_nrm = np.vstack(normal_list)
+        downsampled_max_rec_pts, idx = PtsUtil.voxel_downsample_point_cloud(max_rec_pts, threshold, require_idx=True)
+        downsampled_max_rec_nrm = max_rec_nrm[idx]  
+        
+        max_rec_pts_num = downsampled_max_rec_pts.shape[0]
+        try:
+            max_real_rec_pts_coverage, _ = ReconstructionUtil.compute_coverage_rate_with_normal(target_point_cloud, downsampled_max_rec_pts, target_normal, downsampled_max_rec_nrm, threshold)
+        except:
+            import ipdb; ipdb.set_trace()
+        
+        new_coverage, new_covered_num = ReconstructionUtil.compute_coverage_rate_with_normal(downsampled_max_rec_pts, combined_point_cloud, downsampled_max_rec_nrm, combined_normal, threshold)
+        current_coverage = new_coverage
+        current_covered_num = new_covered_num
+        
+        remaining_views = list(range(len(point_cloud_list)))
+        view_sequence = [(init_view, current_coverage)]
+        cnt_processed_view = 0
+        remaining_views.remove(init_view)
+        curr_rec_pts_num = combined_point_cloud.shape[0]
+        
+        while remaining_views:
+            best_view = None
+            best_coverage_increase = -1
+            best_combined_point_cloud = None
+            best_combined_normal = None
+            best_covered_num = 0
+        
+            for view_index in remaining_views:
+                if point_cloud_list[view_index].shape[0] == 0:
+                    continue
+                if selected_views:
+                    new_scan_points_indices = scan_points_indices_list[view_index]
+                    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
+                        
+                    if not ReconstructionUtil.check_overlap(point_cloud_list[view_index], combined_point_cloud, overlap_area_threshold = curr_overlap_area_threshold, voxel_size=threshold):
+                        continue
+                
+                new_combined_point_cloud = np.vstack([combined_point_cloud, point_cloud_list[view_index]])
+                new_combined_normal = np.vstack([combined_normal, normal_list[view_index]])
+                new_downsampled_combined_point_cloud = PtsUtil.voxel_downsample_point_cloud(new_combined_point_cloud,threshold)
+                new_downsampled_combined_normal = new_combined_normal[idx]
+                new_coverage, new_covered_num = ReconstructionUtil.compute_coverage_rate_with_normal(downsampled_max_rec_pts, new_downsampled_combined_point_cloud, downsampled_max_rec_nrm, new_downsampled_combined_normal, threshold)
+                coverage_increase = new_coverage - current_coverage
+                if coverage_increase > best_coverage_increase:
+                    best_coverage_increase = coverage_increase
+                    best_view = view_index
+                    best_covered_num = new_covered_num
+                    best_combined_point_cloud = new_downsampled_combined_point_cloud
+                    best_combined_normal = new_downsampled_combined_normal
+                    
+            
             if best_view is not None:
                 if best_coverage_increase <=1e-3 or best_covered_num - current_covered_num <= 5:
                     break
@@ -118,6 +207,7 @@ class ReconstructionUtil:
                 current_covered_num = best_covered_num
                 curr_rec_pts_num = best_rec_pts_num
                 combined_point_cloud = best_combined_point_cloud
+                combined_normal = best_combined_normal
                 remaining_views.remove(best_view)
                 history_indices.append(scan_points_indices_list[best_view])
                 current_coverage += best_coverage_increase

utils/vis.py

@@ -48,6 +48,42 @@ class visualizeUtil:
         downsampled_all_pts = PtsUtil.voxel_downsample_point_cloud(all_combined_pts, 0.001)
         np.savetxt(os.path.join(output_dir, "all_combined_pts.txt"), downsampled_all_pts)
 
+    @staticmethod
+    def save_seq_cam_pos_and_cam_axis(root, scene, frame_idx_list, output_dir):
+        all_cam_pos = []
+        all_cam_axis = []
+        for i in frame_idx_list:
+            path = DataLoadUtil.get_path(root, scene, i)
+            cam_info = DataLoadUtil.load_cam_info(path, binocular=True)
+            cam_pose = cam_info["cam_to_world"]
+            cam_pos = cam_pose[:3, 3]
+            cam_axis = cam_pose[:3, 2] 
+            
+            num_samples = 10
+            sample_points = [cam_pos + 0.02*t * cam_axis for t in range(num_samples)]
+            sample_points = np.array(sample_points)
+        
+            all_cam_pos.append(cam_pos)
+            all_cam_axis.append(sample_points)
+        
+        all_cam_pos = np.array(all_cam_pos)
+        all_cam_axis = np.array(all_cam_axis).reshape(-1, 3)
+        np.savetxt(os.path.join(output_dir, "seq_cam_pos.txt"), all_cam_pos)
+        np.savetxt(os.path.join(output_dir, "seq_cam_axis.txt"), all_cam_axis)
+        
+    @staticmethod
+    def save_seq_combined_pts(root, scene, frame_idx_list, output_dir):
+        all_combined_pts = []   
+        for i in frame_idx_list:
+            path = DataLoadUtil.get_path(root, scene, i)
+            pts = DataLoadUtil.load_from_preprocessed_pts(path,"npy")
+            if pts.shape[0] == 0:
+                continue
+            all_combined_pts.append(pts)
+        all_combined_pts = np.vstack(all_combined_pts)
+        downsampled_all_pts = PtsUtil.voxel_downsample_point_cloud(all_combined_pts, 0.001)
+        np.savetxt(os.path.join(output_dir, "seq_combined_pts.txt"), downsampled_all_pts)
+        
     @staticmethod
     def save_target_mesh_at_world_space(
         root, model_dir, scene_name, display_table_as_world_space_origin=True
@@ -126,12 +162,14 @@ class visualizeUtil:
 # ------ Debug ------
 
 if __name__ == "__main__":
-    root = r"/home/yan20/nbv_rec/project/franka_control/temp"
+    root = r"C:\Document\Local Project\nbv_rec\nbv_reconstruction\temp"
     model_dir = r"H:\\AI\\Datasets\\scaled_object_box_meshes"
     scene = "box"
     output_dir = r"C:\Document\Local Project\nbv_rec\nbv_reconstruction\test"
     
     #visualizeUtil.save_all_cam_pos_and_cam_axis(root, scene, output_dir)
     visualizeUtil.save_all_combined_pts(root, scene, output_dir)
+    visualizeUtil.save_seq_combined_pts(root, scene, [0, 121, 286, 175, 111,366,45,230,232,225,255,17,199,78,60], output_dir)
+    visualizeUtil.save_seq_cam_pos_and_cam_axis(root, scene, [0, 121, 286, 175, 111,366,45,230,232,225,255,17,199,78,60], output_dir)
     visualizeUtil.save_target_mesh_at_world_space(root, model_dir, scene)
     #visualizeUtil.save_points_and_normals(root, scene,"10", output_dir, binocular=True)