add fps

core/nbv_dataset.py

@@ -162,8 +162,8 @@ class NBVReconstructionDataset(BaseDataset):
         )
 
         combined_scanned_views_pts = np.concatenate(scanned_views_pts, axis=0)
-        voxel_downsampled_combined_scanned_pts_np = (
+        voxel_downsampled_combined_scanned_pts_np, _ = (
-            PtsUtil.voxel_downsample_point_cloud(combined_scanned_views_pts, 0.002)
+            PtsUtil.voxelize_points(combined_scanned_views_pts, 0.002)
         )
         random_downsampled_combined_scanned_pts_np = (
             PtsUtil.random_downsample_point_cloud(

utils/pts.py

@@ -12,12 +12,6 @@ class PtsUtil:
         downsampled_pc = o3d_pc.voxel_down_sample(voxel_size)
         return np.asarray(downsampled_pc.points)
     
-    @staticmethod
-    def transform_point_cloud(points, pose_mat):
-        points_h = np.concatenate([points, np.ones((points.shape[0], 1))], axis=1)
-        points_h = np.dot(pose_mat, points_h.T).T
-        return points_h[:, :3]
-    
     @staticmethod
     def random_downsample_point_cloud(point_cloud, num_points, require_idx=False):
         if point_cloud.shape[0] == 0:
@@ -29,6 +23,28 @@ class PtsUtil:
             return point_cloud[idx], idx
         return point_cloud[idx]
     
+    @staticmethod
+    def fps_downsample_point_cloud(point_cloud, num_points, require_mask=False):
+        N = point_cloud.shape[0]
+        mask = np.zeros(N, dtype=bool)
+
+        sampled_indices = np.zeros(num_points, dtype=int)
+        sampled_indices[0] = np.random.randint(0, N)
+        mask[sampled_indices[0]] = True
+        distances = np.linalg.norm(point_cloud - point_cloud[sampled_indices[0]], axis=1)
+        for i in range(1, num_points):
+            farthest_index = np.argmax(distances)
+            sampled_indices[i] = farthest_index
+            mask[farthest_index] = True
+
+            new_distances = np.linalg.norm(point_cloud - point_cloud[farthest_index], axis=1)
+            distances = np.minimum(distances, new_distances)
+        
+        sampled_points = point_cloud[sampled_indices]
+        if require_mask:
+            return sampled_points, mask
+        return sampled_points
+        
     @staticmethod
     def random_downsample_point_cloud_tensor(point_cloud, num_points):
         idx = torch.randint(0, len(point_cloud), (num_points,))
@@ -40,6 +56,12 @@ class PtsUtil:
         unique_voxels = np.unique(voxel_indices, axis=0, return_inverse=True)
         return unique_voxels
 
+    @staticmethod
+    def transform_point_cloud(points, pose_mat):
+        points_h = np.concatenate([points, np.ones((points.shape[0], 1))], axis=1)
+        points_h = np.dot(pose_mat, points_h.T).T
+        return points_h[:, :3]
+    
     @staticmethod
     def get_overlapping_points(point_cloud_L, point_cloud_R, voxel_size=0.005, require_idx=False):
         voxels_L, indices_L = PtsUtil.voxelize_points(point_cloud_L, voxel_size)
@@ -56,18 +78,6 @@ class PtsUtil:
             return overlapping_points, mask_L
         return overlapping_points
     
-    @staticmethod
-    def new_filter_points(points, normals, cam_pose, theta=75, require_idx=False):
-        camera_axis = -cam_pose[:3, 2] 
-        normals_normalized = normals / np.linalg.norm(normals, axis=1, keepdims=True)
-        cos_theta = np.dot(normals_normalized, camera_axis)
-        theta_rad = np.deg2rad(theta)
-        idx = cos_theta > np.cos(theta_rad)
-        filtered_points= points[idx]
-        if require_idx:
-            return filtered_points, idx
-        return filtered_points
-    
     @staticmethod
     def filter_points(points, points_normals, cam_pose,  voxel_size=0.002, theta=45, z_range=(0.2, 0.45)):