diff --git a/configs/local/view_generate_config.yaml b/configs/local/view_generate_config.yaml index c9a5234..1266f37 100644 --- a/configs/local/view_generate_config.yaml +++ b/configs/local/view_generate_config.yaml @@ -7,9 +7,9 @@ runner: name: debug root_dir: experiments generate: - port: 5002 - from: 2200 - to: 2300 # -1 means all + port: 5005 + from: 2300 + to: 2800 # -1 means all object_dir: /media/hofee/data/data/scaled_object_meshes table_model_path: /media/hofee/data/data/others/table.obj output_dir: /media/hofee/repository/new_data_with_normal @@ -49,4 +49,4 @@ runner: Light: location: [0,0,3.5] orientation: [0,0,0] - power: 150 + power: 150 \ No newline at end of file diff --git a/preprocess/preprocessor.py b/preprocess/preprocessor.py index eea33c9..c8a065a 100644 --- a/preprocess/preprocessor.py +++ b/preprocess/preprocessor.py @@ -30,13 +30,15 @@ def save_target_points(root, scene, frame_idx, target_points: np.ndarray, file_t os.makedirs(os.path.join(root,scene, "target_pts")) save_np_pts(pts_path, target_points, file_type) -def save_mask_idx(root, scene, frame_idx, mask_idx: np.ndarray,filtered_idx, file_type="txt"): - indices_path = os.path.join(root,scene, "mask_idx", f"{frame_idx}.{file_type}") +def save_mask_idx(root, scene, frame_idx, mask_train_input: np.ndarray, mask_overlap, file_type="txt"): + mask_train_input_path = os.path.join(root,scene, "mask_idx", f"mask_train_input_{frame_idx}.{file_type}") + mask_overlap_path = os.path.join(root,scene, "mask_idx", f"mask_overlap_{frame_idx}.{file_type}") if not os.path.exists(os.path.join(root,scene, "mask_idx")): os.makedirs(os.path.join(root,scene, "mask_idx")) - save_np_pts(indices_path, mask_idx, file_type) - filtered_path = os.path.join(root,scene, "mask_idx", f"{frame_idx}_filtered.{file_type}") - save_np_pts(filtered_path, filtered_idx, file_type) + save_np_pts(mask_train_input_path, mask_train_input, file_type) + save_np_pts(mask_overlap_path, mask_overlap, file_type) + # filtered_path = os.path.join(root,scene, "mask_idx", f"{frame_idx}_filtered.{file_type}") + # save_np_pts(filtered_path, filtered_idx, file_type) def save_scan_points_indices(root, scene, frame_idx, scan_points_indices: np.ndarray, file_type="txt"): indices_path = os.path.join(root,scene, "scan_points_indices", f"{frame_idx}.{file_type}") @@ -62,14 +64,9 @@ def get_world_points(depth, cam_intrinsic, cam_extrinsic): points_camera_world = np.dot(cam_extrinsic, points_camera_aug.T).T[:, :3] return points_camera_world -def get_world_normals(normals, cam_extrinsic): - normals = normals / np.linalg.norm(normals, axis=1, keepdims=True) - normals_world = np.dot(cam_extrinsic[:3, :3], normals.T).T - return normals_world - 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(cam_extrinsic, scan_points_homogeneous.T).T[:, :3] + 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) @@ -77,11 +74,12 @@ def get_scan_points_indices(scan_points, mask, display_table_mask_label, cam_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 = mask_colors == display_table_mask_label + 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 -def save_scene_data(root, scene, scene_idx=0, scene_total=1): +def save_scene_data(root, scene, scene_idx=0, scene_total=1,file_type="txt"): ''' configuration ''' target_mask_label = (0, 255, 0, 255) @@ -99,7 +97,11 @@ def save_scene_data(root, scene, scene_idx=0, scene_total=1): ''' read frame data(depth|mask|normal) ''' frame_num = DataLoadUtil.get_scene_seq_length(root, scene) for frame_id in range(frame_num): + + print(f"[scene({scene_idx}/{scene_total})|frame({frame_id}/{frame_num})]Processing {scene} frame {frame_id}") + if frame_id != 126: + continue path = DataLoadUtil.get_path(root, scene, frame_id) cam_info = DataLoadUtil.load_cam_info(path, binocular=True) depth_L, depth_R = DataLoadUtil.load_depth( @@ -107,8 +109,8 @@ def save_scene_data(root, scene, scene_idx=0, scene_total=1): cam_info["far_plane"], binocular=True ) - mask_L = DataLoadUtil.load_seg(path, binocular=True, left_only=True) - normal_L = DataLoadUtil.load_normal(path, binocular=True, left_only=True) + mask_L, mask_R = DataLoadUtil.load_seg(path, binocular=True) + #normal_L = DataLoadUtil.load_normal(path, binocular=True, left_only=True) ''' scene points ''' scene_points_L = get_world_points(depth_L, cam_info["cam_intrinsic"], cam_info["cam_to_world"]) @@ -131,28 +133,30 @@ def save_scene_data(root, scene, scene_idx=0, scene_total=1): ) ''' target points ''' - mask_img = mask_L + mask_img_L = mask_L + mask_img_R = mask_R mask_L = mask_L.reshape(-1, 4) mask_L = (mask_L == target_mask_label).all(axis=-1) mask_overlap = mask_L[random_sample_idx_L][overlap_idx_L] - scene_normals_L = normal_L.reshape(-1, 3) - target_overlap_normals = scene_normals_L[random_sample_idx_L][overlap_idx_L][mask_overlap] - target_normals = get_world_normals(target_overlap_normals, cam_info["cam_to_world"]) target_points = scene_overlap_points[mask_overlap] filtered_target_points, filtered_idx = PtsUtil.filter_points( target_points, target_normals, cam_info["cam_to_world"], filter_degree, require_idx=True ) - + ''' train_input_mask ''' mask_train_input = mask_overlap[train_input_idx] ''' scan points indices ''' - scan_points_indices = get_scan_points_indices(scan_points, mask_img, display_table_mask_label, cam_info["cam_intrinsic"], cam_info["cam_to_world"]) - - save_full_points(root, scene, frame_id, train_input_points) - save_target_points(root, scene, frame_id, filtered_target_points) - save_mask_idx(root, scene, frame_id, mask_train_input, filtered_idx=filtered_idx) + scan_points_indices_L = get_scan_points_indices(scan_points, mask_img_L, display_table_mask_label, cam_info["cam_intrinsic"], cam_info["cam_to_world"]) + scan_points_indices_R = get_scan_points_indices(scan_points, mask_img_R, 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) + print(scan_points_indices.shape, scan_points_indices_L.shape, scan_points_indices_R.shape) + # np.savetxt(f"{root}/{scene}/scan_points_{frame_id}_L.txt", scan_points[scan_points_indices_L]) + np.savetxt(f"{root}/{scene}/scan_points_{frame_id}.txt", scan_points[scan_points_indices]) + save_full_points(root, scene, frame_id, train_input_points, file_type=file_type) + save_target_points(root, scene, frame_id, target_points) + save_mask_idx(root, scene, frame_id, mask_train_input, mask_overlap,file_type=file_type) save_scan_points_indices(root, scene, frame_id, scan_points_indices) save_scan_points(root, scene, scan_points) # The "done" flag of scene preprocess @@ -170,8 +174,10 @@ if __name__ == "__main__": from_idx = 0 to_idx = len(scene_list) + + cnt = 0 total = to_idx - from_idx for scene in scene_list[from_idx:to_idx]: - save_scene_data(root, scene, cnt, total) + save_scene_data(root, scene, cnt, total, "txt") cnt+=1 \ No newline at end of file