import os os.environ["EGL_PLATFORM"] = "surfaceless" import open3d as o3d import numpy as np import json import argparse from concurrent.futures import ThreadPoolExecutor from typing import List, Tuple, Optional # from scripts.colmap_loader import read_images_text, read_cameras_text # # Copyright (C) 2023, Inria # GRAPHDECO research group, https://team.inria.fr/graphdeco # All rights reserved. # # This software is free for non-commercial, research and evaluation use # under the terms of the LICENSE.md file. # # For inquiries contact george.drettakis@inria.fr # import numpy as np import collections import struct import math import os CameraModel = collections.namedtuple( "CameraModel", ["model_id", "model_name", "num_params"] ) Camera = collections.namedtuple("Camera", ["id", "model", "width", "height", "params"]) BaseImage = collections.namedtuple( "Image", ["id", "qvec", "tvec", "camera_id", "name", "xys", "point3D_ids"] ) Point3D = collections.namedtuple( "Point3D", ["id", "xyz", "rgb", "error", "image_ids", "point2D_idxs"] ) CAMERA_MODELS = { CameraModel(model_id=0, model_name="SIMPLE_PINHOLE", num_params=3), CameraModel(model_id=1, model_name="PINHOLE", num_params=4), CameraModel(model_id=2, model_name="SIMPLE_RADIAL", num_params=4), CameraModel(model_id=3, model_name="RADIAL", num_params=5), CameraModel(model_id=4, model_name="OPENCV", num_params=8), CameraModel(model_id=5, model_name="OPENCV_FISHEYE", num_params=8), CameraModel(model_id=6, model_name="FULL_OPENCV", num_params=12), CameraModel(model_id=7, model_name="FOV", num_params=5), CameraModel(model_id=8, model_name="SIMPLE_RADIAL_FISHEYE", num_params=4), CameraModel(model_id=9, model_name="RADIAL_FISHEYE", num_params=5), CameraModel(model_id=10, model_name="THIN_PRISM_FISHEYE", num_params=12), } CAMERA_MODEL_IDS = dict( [(camera_model.model_id, camera_model) for camera_model in CAMERA_MODELS] ) CAMERA_MODEL_NAMES = dict( [(camera_model.model_name, camera_model) for camera_model in CAMERA_MODELS] ) def qvec2rotmat(qvec): return np.array( [ [ 1 - 2 * qvec[2] ** 2 - 2 * qvec[3] ** 2, 2 * qvec[1] * qvec[2] - 2 * qvec[0] * qvec[3], 2 * qvec[3] * qvec[1] + 2 * qvec[0] * qvec[2], ], [ 2 * qvec[1] * qvec[2] + 2 * qvec[0] * qvec[3], 1 - 2 * qvec[1] ** 2 - 2 * qvec[3] ** 2, 2 * qvec[2] * qvec[3] - 2 * qvec[0] * qvec[1], ], [ 2 * qvec[3] * qvec[1] - 2 * qvec[0] * qvec[2], 2 * qvec[2] * qvec[3] + 2 * qvec[0] * qvec[1], 1 - 2 * qvec[1] ** 2 - 2 * qvec[2] ** 2, ], ] ) def rotmat2qvec(R): Rxx, Ryx, Rzx, Rxy, Ryy, Rzy, Rxz, Ryz, Rzz = R.flat K = ( np.array( [ [Rxx - Ryy - Rzz, 0, 0, 0], [Ryx + Rxy, Ryy - Rxx - Rzz, 0, 0], [Rzx + Rxz, Rzy + Ryz, Rzz - Rxx - Ryy, 0], [Ryz - Rzy, Rzx - Rxz, Rxy - Ryx, Rxx + Ryy + Rzz], ] ) / 3.0 ) eigvals, eigvecs = np.linalg.eigh(K) qvec = eigvecs[[3, 0, 1, 2], np.argmax(eigvals)] if qvec[0] < 0: qvec *= -1 return qvec class Image(BaseImage): def qvec2rotmat(self): return qvec2rotmat(self.qvec) def read_next_bytes(fid, num_bytes, format_char_sequence, endian_character="<"): """Read and unpack the next bytes from a binary file. :param fid: :param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc. :param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}. :param endian_character: Any of {@, =, <, >, !} :return: Tuple of read and unpacked values. """ data = fid.read(num_bytes) return struct.unpack(endian_character + format_char_sequence, data) def read_points3D_text(path): """ see: src/base/reconstruction.cc void Reconstruction::ReadPoints3DText(const std::string& path) void Reconstruction::WritePoints3DText(const std::string& path) """ xyzs = None rgbs = None errors = None num_points = 0 with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": num_points += 1 xyzs = np.empty((num_points, 3)) rgbs = np.empty((num_points, 3)) errors = np.empty((num_points, 1)) count = 0 with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": elems = line.split() xyz = np.array(tuple(map(float, elems[1:4]))) rgb = np.array(tuple(map(int, elems[4:7]))) error = np.array(float(elems[7])) xyzs[count] = xyz rgbs[count] = rgb errors[count] = error count += 1 return xyzs, rgbs, errors def read_points3D_binary(path_to_model_file): """ see: src/base/reconstruction.cc void Reconstruction::ReadPoints3DBinary(const std::string& path) void Reconstruction::WritePoints3DBinary(const std::string& path) """ with open(path_to_model_file, "rb") as fid: num_points = read_next_bytes(fid, 8, "Q")[0] xyzs = np.empty((num_points, 3)) rgbs = np.empty((num_points, 3)) errors = np.empty((num_points, 1)) for p_id in range(num_points): binary_point_line_properties = read_next_bytes( fid, num_bytes=43, format_char_sequence="QdddBBBd" ) xyz = np.array(binary_point_line_properties[1:4]) rgb = np.array(binary_point_line_properties[4:7]) error = np.array(binary_point_line_properties[7]) track_length = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[ 0 ] track_elems = read_next_bytes( fid, num_bytes=8 * track_length, format_char_sequence="ii" * track_length, ) xyzs[p_id] = xyz rgbs[p_id] = rgb errors[p_id] = error return xyzs, rgbs, errors def read_intrinsics_text(path): """ Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py """ cameras = {} with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": elems = line.split() camera_id = int(elems[0]) model = elems[1] assert ( model == "PINHOLE" ), "While the loader support other types, the rest of the code assumes PINHOLE" width = int(elems[2]) height = int(elems[3]) params = np.array(tuple(map(float, elems[4:]))) cameras[camera_id] = Camera( id=camera_id, model=model, width=width, height=height, params=params ) return cameras def read_extrinsics_binary(path_to_model_file): """ see: src/base/reconstruction.cc void Reconstruction::ReadImagesBinary(const std::string& path) void Reconstruction::WriteImagesBinary(const std::string& path) """ images = {} with open(path_to_model_file, "rb") as fid: num_reg_images = read_next_bytes(fid, 8, "Q")[0] for _ in range(num_reg_images): binary_image_properties = read_next_bytes( fid, num_bytes=64, format_char_sequence="idddddddi" ) image_id = binary_image_properties[0] qvec = np.array(binary_image_properties[1:5]) tvec = np.array(binary_image_properties[5:8]) camera_id = binary_image_properties[8] image_name = "" current_char = read_next_bytes(fid, 1, "c")[0] while current_char != b"\x00": # look for the ASCII 0 entry image_name += current_char.decode("utf-8") current_char = read_next_bytes(fid, 1, "c")[0] num_points2D = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[ 0 ] x_y_id_s = read_next_bytes( fid, num_bytes=24 * num_points2D, format_char_sequence="ddq" * num_points2D, ) xys = np.column_stack( [tuple(map(float, x_y_id_s[0::3])), tuple(map(float, x_y_id_s[1::3]))] ) point3D_ids = np.array(tuple(map(int, x_y_id_s[2::3]))) images[image_id] = Image( id=image_id, qvec=qvec, tvec=tvec, camera_id=camera_id, name=image_name, xys=xys, point3D_ids=point3D_ids, ) return images def read_intrinsics_binary(path_to_model_file): """ see: src/base/reconstruction.cc void Reconstruction::WriteCamerasBinary(const std::string& path) void Reconstruction::ReadCamerasBinary(const std::string& path) """ cameras = {} with open(path_to_model_file, "rb") as fid: num_cameras = read_next_bytes(fid, 8, "Q")[0] for _ in range(num_cameras): camera_properties = read_next_bytes( fid, num_bytes=24, format_char_sequence="iiQQ" ) camera_id = camera_properties[0] model_id = camera_properties[1] model_name = CAMERA_MODEL_IDS[camera_properties[1]].model_name width = camera_properties[2] height = camera_properties[3] num_params = CAMERA_MODEL_IDS[model_id].num_params params = read_next_bytes( fid, num_bytes=8 * num_params, format_char_sequence="d" * num_params ) cameras[camera_id] = Camera( id=camera_id, model=model_name, width=width, height=height, params=np.array(params), ) assert len(cameras) == num_cameras return cameras def focal2fov(focal, pixels): return 2 * math.atan(pixels / (2 * focal)) def read_extrinsics_text(path): """ Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_write_model.py """ images = {} with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": elems = line.split() image_id = int(elems[0]) qvec = np.array(tuple(map(float, elems[1:5]))) tvec = np.array(tuple(map(float, elems[5:8]))) camera_id = int(elems[8]) image_name = elems[9] elems = fid.readline().split() xys = np.column_stack( [tuple(map(float, elems[0::3])), tuple(map(float, elems[1::3]))] ) point3D_ids = np.array(tuple(map(int, elems[2::3]))) images[image_id] = Image( id=image_id, qvec=qvec, tvec=tvec, camera_id=camera_id, name=image_name, xys=xys, point3D_ids=point3D_ids, ) return images def read_colmap_bin_array(path): """ Taken from https://github.com/colmap/colmap/blob/dev/scripts/python/read_dense.py :param path: path to the colmap binary file. :return: nd array with the floating point values in the value """ with open(path, "rb") as fid: width, height, channels = np.genfromtxt( fid, delimiter="&", max_rows=1, usecols=(0, 1, 2), dtype=int ) fid.seek(0) num_delimiter = 0 byte = fid.read(1) while True: if byte == b"&": num_delimiter += 1 if num_delimiter >= 3: break byte = fid.read(1) array = np.fromfile(fid, np.float32) array = array.reshape((width, height, channels), order="F") return np.transpose(array, (1, 0, 2)).squeeze() def read_next_bytes(fid, num_bytes, format_char_sequence, endian_character="<"): """Read and unpack the next bytes from a binary file. :param fid: :param num_bytes: Sum of combination of {2, 4, 8}, e.g. 2, 6, 16, 30, etc. :param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}. :param endian_character: Any of {@, =, <, >, !} :return: Tuple of read and unpacked values. """ data = fid.read(num_bytes) return struct.unpack(endian_character + format_char_sequence, data) def write_next_bytes(fid, data, format_char_sequence, endian_character="<"): """pack and write to a binary file. :param fid: :param data: data to send, if multiple elements are sent at the same time, they should be encapsuled either in a list or a tuple :param format_char_sequence: List of {c, e, f, d, h, H, i, I, l, L, q, Q}. should be the same length as the data list or tuple :param endian_character: Any of {@, =, <, >, !} """ if isinstance(data, (list, tuple)): bytes = struct.pack(endian_character + format_char_sequence, *data) else: bytes = struct.pack(endian_character + format_char_sequence, data) fid.write(bytes) def read_cameras_text(path): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::WriteCamerasText(const std::string& path) void Reconstruction::ReadCamerasText(const std::string& path) """ cameras = {} with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": elems = line.split() camera_id = int(elems[0]) model = elems[1] width = int(elems[2]) height = int(elems[3]) params = np.array(tuple(map(float, elems[4:]))) cameras[camera_id] = Camera( id=camera_id, model=model, width=width, height=height, params=params, ) return cameras def read_cameras_binary(path_to_model_file): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::WriteCamerasBinary(const std::string& path) void Reconstruction::ReadCamerasBinary(const std::string& path) """ cameras = {} with open(path_to_model_file, "rb") as fid: num_cameras = read_next_bytes(fid, 8, "Q")[0] for _ in range(num_cameras): camera_properties = read_next_bytes( fid, num_bytes=24, format_char_sequence="iiQQ" ) camera_id = camera_properties[0] model_id = camera_properties[1] model_name = CAMERA_MODEL_IDS[camera_properties[1]].model_name width = camera_properties[2] height = camera_properties[3] num_params = CAMERA_MODEL_IDS[model_id].num_params params = read_next_bytes( fid, num_bytes=8 * num_params, format_char_sequence="d" * num_params, ) cameras[camera_id] = Camera( id=camera_id, model=model_name, width=width, height=height, params=np.array(params), ) assert len(cameras) == num_cameras return cameras def write_cameras_text(cameras, path): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::WriteCamerasText(const std::string& path) void Reconstruction::ReadCamerasText(const std::string& path) """ HEADER = ( "# Camera list with one line of data per camera:\n" + "# CAMERA_ID, MODEL, WIDTH, HEIGHT, PARAMS[]\n" + "# Number of cameras: {}\n".format(len(cameras)) ) with open(path, "w") as fid: fid.write(HEADER) for _, cam in cameras.items(): to_write = [cam.id, cam.model, cam.width, cam.height, *cam.params] line = " ".join([str(elem) for elem in to_write]) fid.write(line + "\n") def write_cameras_binary(cameras, path_to_model_file): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::WriteCamerasBinary(const std::string& path) void Reconstruction::ReadCamerasBinary(const std::string& path) """ with open(path_to_model_file, "wb") as fid: write_next_bytes(fid, len(cameras), "Q") for _, cam in cameras.items(): model_id = CAMERA_MODEL_NAMES[cam.model].model_id camera_properties = [cam.id, model_id, cam.width, cam.height] write_next_bytes(fid, camera_properties, "iiQQ") for p in cam.params: write_next_bytes(fid, float(p), "d") return cameras def read_images_text(path): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadImagesText(const std::string& path) void Reconstruction::WriteImagesText(const std::string& path) """ images = {} with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": elems = line.split() image_id = int(elems[0]) qvec = np.array(tuple(map(float, elems[1:5]))) tvec = np.array(tuple(map(float, elems[5:8]))) camera_id = int(elems[8]) image_name = elems[9] elems = fid.readline().split() xys = np.column_stack( [ tuple(map(float, elems[0::3])), tuple(map(float, elems[1::3])), ] ) point3D_ids = np.array(tuple(map(int, elems[2::3]))) images[image_id] = Image( id=image_id, qvec=qvec, tvec=tvec, camera_id=camera_id, name=image_name, xys=xys, point3D_ids=point3D_ids, ) return images def read_images_binary(path_to_model_file): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadImagesBinary(const std::string& path) void Reconstruction::WriteImagesBinary(const std::string& path) """ images = {} with open(path_to_model_file, "rb") as fid: num_reg_images = read_next_bytes(fid, 8, "Q")[0] for _ in range(num_reg_images): binary_image_properties = read_next_bytes( fid, num_bytes=64, format_char_sequence="idddddddi" ) image_id = binary_image_properties[0] qvec = np.array(binary_image_properties[1:5]) tvec = np.array(binary_image_properties[5:8]) camera_id = binary_image_properties[8] binary_image_name = b"" current_char = read_next_bytes(fid, 1, "c")[0] while current_char != b"\x00": # look for the ASCII 0 entry binary_image_name += current_char current_char = read_next_bytes(fid, 1, "c")[0] image_name = binary_image_name.decode("utf-8") num_points2D = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[ 0 ] x_y_id_s = read_next_bytes( fid, num_bytes=24 * num_points2D, format_char_sequence="ddq" * num_points2D, ) xys = np.column_stack( [ tuple(map(float, x_y_id_s[0::3])), tuple(map(float, x_y_id_s[1::3])), ] ) point3D_ids = np.array(tuple(map(int, x_y_id_s[2::3]))) images[image_id] = Image( id=image_id, qvec=qvec, tvec=tvec, camera_id=camera_id, name=image_name, xys=xys, point3D_ids=point3D_ids, ) return images def write_images_text(images, path): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadImagesText(const std::string& path) void Reconstruction::WriteImagesText(const std::string& path) """ if len(images) == 0: mean_observations = 0 else: mean_observations = sum( (len(img.point3D_ids) for _, img in images.items()) ) / len(images) HEADER = ( "# Image list with two lines of data per image:\n" + "# IMAGE_ID, QW, QX, QY, QZ, TX, TY, TZ, CAMERA_ID, NAME\n" + "# POINTS2D[] as (X, Y, POINT3D_ID)\n" + "# Number of images: {}, mean observations per image: {}\n".format( len(images), mean_observations ) ) with open(path, "w") as fid: fid.write(HEADER) for _, img in images.items(): image_header = [ img.id, *img.qvec, *img.tvec, img.camera_id, img.name, ] first_line = " ".join(map(str, image_header)) fid.write(first_line + "\n") points_strings = [] for xy, point3D_id in zip(img.xys, img.point3D_ids): points_strings.append(" ".join(map(str, [*xy, point3D_id]))) fid.write(" ".join(points_strings) + "\n") def write_images_binary(images, path_to_model_file): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadImagesBinary(const std::string& path) void Reconstruction::WriteImagesBinary(const std::string& path) """ with open(path_to_model_file, "wb") as fid: write_next_bytes(fid, len(images), "Q") for _, img in images.items(): write_next_bytes(fid, img.id, "i") write_next_bytes(fid, img.qvec.tolist(), "dddd") write_next_bytes(fid, img.tvec.tolist(), "ddd") write_next_bytes(fid, img.camera_id, "i") for char in img.name: write_next_bytes(fid, char.encode("utf-8"), "c") write_next_bytes(fid, b"\x00", "c") write_next_bytes(fid, len(img.point3D_ids), "Q") for xy, p3d_id in zip(img.xys, img.point3D_ids): write_next_bytes(fid, [*xy, p3d_id], "ddq") def read_points3D_text(path): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadPoints3DText(const std::string& path) void Reconstruction::WritePoints3DText(const std::string& path) """ points3D = {} with open(path, "r") as fid: while True: line = fid.readline() if not line: break line = line.strip() if len(line) > 0 and line[0] != "#": elems = line.split() point3D_id = int(elems[0]) xyz = np.array(tuple(map(float, elems[1:4]))) rgb = np.array(tuple(map(int, elems[4:7]))) error = float(elems[7]) image_ids = np.array(tuple(map(int, elems[8::2]))) point2D_idxs = np.array(tuple(map(int, elems[9::2]))) points3D[point3D_id] = Point3D( id=point3D_id, xyz=xyz, rgb=rgb, error=error, image_ids=image_ids, point2D_idxs=point2D_idxs, ) return points3D def read_points3D_binary(path_to_model_file): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadPoints3DBinary(const std::string& path) void Reconstruction::WritePoints3DBinary(const std::string& path) """ points3D = {} with open(path_to_model_file, "rb") as fid: num_points = read_next_bytes(fid, 8, "Q")[0] for _ in range(num_points): binary_point_line_properties = read_next_bytes( fid, num_bytes=43, format_char_sequence="QdddBBBd" ) point3D_id = binary_point_line_properties[0] xyz = np.array(binary_point_line_properties[1:4]) rgb = np.array(binary_point_line_properties[4:7]) error = np.array(binary_point_line_properties[7]) track_length = read_next_bytes(fid, num_bytes=8, format_char_sequence="Q")[ 0 ] track_elems = read_next_bytes( fid, num_bytes=8 * track_length, format_char_sequence="ii" * track_length, ) image_ids = np.array(tuple(map(int, track_elems[0::2]))) point2D_idxs = np.array(tuple(map(int, track_elems[1::2]))) points3D[point3D_id] = Point3D( id=point3D_id, xyz=xyz, rgb=rgb, error=error, image_ids=image_ids, point2D_idxs=point2D_idxs, ) return points3D def write_points3D_text(points3D, path): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadPoints3DText(const std::string& path) void Reconstruction::WritePoints3DText(const std::string& path) """ if len(points3D) == 0: mean_track_length = 0 else: mean_track_length = sum( (len(pt.image_ids) for _, pt in points3D.items()) ) / len(points3D) HEADER = ( "# 3D point list with one line of data per point:\n" + "# POINT3D_ID, X, Y, Z, R, G, B, ERROR, TRACK[] as (IMAGE_ID, POINT2D_IDX)\n" + "# Number of points: {}, mean track length: {}\n".format( len(points3D), mean_track_length ) ) with open(path, "w") as fid: fid.write(HEADER) for _, pt in points3D.items(): point_header = [pt.id, *pt.xyz, *pt.rgb, pt.error] fid.write(" ".join(map(str, point_header)) + " ") track_strings = [] for image_id, point2D in zip(pt.image_ids, pt.point2D_idxs): track_strings.append(" ".join(map(str, [image_id, point2D]))) fid.write(" ".join(track_strings) + "\n") def write_points3D_binary(points3D, path_to_model_file): """ see: src/colmap/scene/reconstruction.cc void Reconstruction::ReadPoints3DBinary(const std::string& path) void Reconstruction::WritePoints3DBinary(const std::string& path) """ with open(path_to_model_file, "wb") as fid: write_next_bytes(fid, len(points3D), "Q") for _, pt in points3D.items(): write_next_bytes(fid, pt.id, "Q") write_next_bytes(fid, pt.xyz.tolist(), "ddd") write_next_bytes(fid, pt.rgb.tolist(), "BBB") write_next_bytes(fid, pt.error, "d") track_length = pt.image_ids.shape[0] write_next_bytes(fid, track_length, "Q") for image_id, point2D_id in zip(pt.image_ids, pt.point2D_idxs): write_next_bytes(fid, [image_id, point2D_id], "ii") def detect_model_format(path, ext): if ( os.path.isfile(os.path.join(path, "cameras" + ext)) and os.path.isfile(os.path.join(path, "images" + ext)) and os.path.isfile(os.path.join(path, "points3D" + ext)) ): print("Detected model format: '" + ext + "'") return True return False def read_model(path, ext=""): # try to detect the extension automatically if ext == "": if detect_model_format(path, ".bin"): ext = ".bin" elif detect_model_format(path, ".txt"): ext = ".txt" else: print("Provide model format: '.bin' or '.txt'") return if ext == ".txt": cameras = read_cameras_text(os.path.join(path, "cameras" + ext)) images = read_images_text(os.path.join(path, "images" + ext)) points3D = read_points3D_text(os.path.join(path, "points3D") + ext) else: cameras = read_cameras_binary(os.path.join(path, "cameras" + ext)) images = read_images_binary(os.path.join(path, "images" + ext)) points3D = read_points3D_binary(os.path.join(path, "points3D") + ext) return cameras, images, points3D def write_model(cameras, images, points3D, path, ext=".bin"): if ext == ".txt": write_cameras_text(cameras, os.path.join(path, "cameras" + ext)) write_images_text(images, os.path.join(path, "images" + ext)) write_points3D_text(points3D, os.path.join(path, "points3D") + ext) else: write_cameras_binary(cameras, os.path.join(path, "cameras" + ext)) write_images_binary(images, os.path.join(path, "images" + ext)) write_points3D_binary(points3D, os.path.join(path, "points3D") + ext) return cameras, images, points3D def qvec2rotmat(qvec): return np.array( [ [ 1 - 2 * qvec[2] ** 2 - 2 * qvec[3] ** 2, 2 * qvec[1] * qvec[2] - 2 * qvec[0] * qvec[3], 2 * qvec[3] * qvec[1] + 2 * qvec[0] * qvec[2], ], [ 2 * qvec[1] * qvec[2] + 2 * qvec[0] * qvec[3], 1 - 2 * qvec[1] ** 2 - 2 * qvec[3] ** 2, 2 * qvec[2] * qvec[3] - 2 * qvec[0] * qvec[1], ], [ 2 * qvec[3] * qvec[1] - 2 * qvec[0] * qvec[2], 2 * qvec[2] * qvec[3] + 2 * qvec[0] * qvec[1], 1 - 2 * qvec[1] ** 2 - 2 * qvec[2] ** 2, ], ] ) def rotmat2qvec(R): Rxx, Ryx, Rzx, Rxy, Ryy, Rzy, Rxz, Ryz, Rzz = R.flat K = ( np.array( [ [Rxx - Ryy - Rzz, 0, 0, 0], [Ryx + Rxy, Ryy - Rxx - Rzz, 0, 0], [Rzx + Rxz, Rzy + Ryz, Rzz - Rxx - Ryy, 0], [Ryz - Rzy, Rzx - Rxz, Rxy - Ryx, Rxx + Ryy + Rzz], ] ) / 3.0 ) eigvals, eigvecs = np.linalg.eigh(K) qvec = eigvecs[[3, 0, 1, 2], np.argmax(eigvals)] if qvec[0] < 0: qvec *= -1 return qvec class DepthRenderer: """ 复用渲染器的深度图渲染类 """ def __init__(self, mesh: o3d.geometry.TriangleMesh, width: int, height: int): """ 初始化渲染器，只加载一次模型 参数: mesh (o3d.geometry.TriangleMesh): 要渲染的3D网格 width (int): 渲染图像的宽度 height (int): 渲染图像的高度 """ self.width = width self.height = height # 创建渲染器（只创建一次） self.render = o3d.visualization.rendering.OffscreenRenderer(width, height) # 将 mesh 加载到渲染器（只加载一次） material = o3d.visualization.rendering.MaterialRecord() self.render.scene.add_geometry("mesh", mesh, material) # 确保渲染器正确初始化 if not self.render: raise RuntimeError("Renderer failed to initialize.") def render_depth_map(self, K: np.ndarray, R: np.ndarray, t: np.ndarray) -> Tuple[np.ndarray, float]: """ 渲染深度图，复用已初始化的渲染器 参数: K (np.array): 相机内参矩阵 R (np.array): 相机旋转矩阵 t (np.array): 相机平移向量 返回: tuple: 包含深度图（未归一化）和最大深度值 """ # 设置相机投影矩阵 fx, fy, cx, cy = K[0, 0], K[1, 1], K[0, 2], K[1, 2] intrinsic = o3d.camera.PinholeCameraIntrinsic(self.width, self.height, fx, fy, cx, cy) # 将外参转换为 4x4 变换矩阵 (从 R 和 t) extrinsic = np.eye(4) extrinsic[:3, :3] = R extrinsic[:3, 3] = t # 设置相机参数（只需要更新相机参数） self.render.setup_camera(intrinsic, extrinsic) # 渲染深度图 depth_image = self.render.render_to_depth_image(z_in_view_space=True) # 检查是否生成了深度图 if depth_image is None: raise RuntimeError("Depth image was not generated.") # 将深度图转换为 numpy 数组 depth_map = np.asarray(depth_image) # 返回未归一化的深度图和最大深度值 max_depth = np.nanmax(depth_map) # 获取最大深度值 return depth_map, max_depth def save_depth_map_async(depth_data: Tuple[str, np.ndarray, float], output_path: str) -> None: """ 异步保存深度图的函数 参数: depth_data: 包含(文件名, 深度图, 最大深度值)的元组 output_path: 输出路径 """ name, depth_map, max_depth = depth_data depth_filename = os.path.join(output_path, f"{name.split('.')[0]}.npz") np.savez_compressed(depth_filename, depth=depth_map, max_depth=max_depth) def generate_depth_maps_and_save_optimized( mesh: o3d.geometry.TriangleMesh, camera_params: List[Tuple[str, np.ndarray, np.ndarray, np.ndarray]], width: int, height: int, output_path: str, max_workers: Optional[int] = None ) -> None: """ 优化版本：生成深度图并异步保存 参数: mesh (o3d.geometry.TriangleMesh): 3D网格 camera_params (list): 相机参数列表 width (int): 图像宽度 height (int): 图像高度 output_path (str): 输出路径 max_workers (int, optional): 异步保存的最大工作线程数 返回: None """ # 确保输出目录存在 os.makedirs(output_path, exist_ok=True) # 创建复用的深度渲染器 depth_renderer = DepthRenderer(mesh, width, height) # 存储待保存的深度图数据 depth_data_list = [] print(f"开始渲染 {len(camera_params)} 张深度图...") # 批量渲染深度图 for i, (name, K, R, t) in enumerate(camera_params): depth_map, max_depth = depth_renderer.render_depth_map(K, R, t) depth_data_list.append((name, depth_map.copy(), max_depth)) if (i + 1) % 10 == 0: print(f"已渲染 {i + 1}/{len(camera_params)} 张图片") print("渲染完成，开始异步保存...") # 使用线程池异步保存所有深度图 with ThreadPoolExecutor(max_workers=max_workers) as executor: futures = [] for depth_data in depth_data_list: future = executor.submit(save_depth_map_async, depth_data, output_path) futures.append(future) # 等待所有保存任务完成，并显示进度 for i, future in enumerate(futures): future.result() # 等待完成并获取结果（如果有异常会抛出） if (i + 1) % 10 == 0: print(f"已保存 {i + 1}/{len(futures)} 个文件") print(f"所有深度图已保存完成到: {output_path}") def render_depth_map(mesh, K, R, t, width, height): """ 渲染深度图，不进行归一化。 注意：此函数保留用于向后兼容，建议使用 DepthRenderer 类以获得更好的性能 参数: mesh (o3d.geometry.TriangleMesh): 要渲染的3D网格 K (np.array): 相机内参矩阵 R (np.array): 相机旋转矩阵 t (np.array): 相机平移向量 width (int): 渲染图像的宽度 height (int): 渲染图像的高度 返回: tuple: 包含深度图（未归一化）和最大深度值 """ # 创建渲染器 render = o3d.visualization.rendering.OffscreenRenderer(width, height) # 设置相机投影矩阵 fx, fy, cx, cy = K[0, 0], K[1, 1], K[0, 2], K[1, 2] intrinsic = o3d.camera.PinholeCameraIntrinsic(width, height, fx, fy, cx, cy) # 将外参转换为 4x4 变换矩阵 (从 R 和 t) extrinsic = np.eye(4) extrinsic[:3, :3] = R extrinsic[:3, 3] = t # 设置相机参数 render.setup_camera(intrinsic, extrinsic) # 将 mesh 加载到渲染器 material = o3d.visualization.rendering.MaterialRecord() render.scene.add_geometry("mesh", mesh, material) # 渲染深度图 depth_image = render.render_to_depth_image(z_in_view_space=True) # 确保渲染器正确初始化 if not render: raise RuntimeError("Renderer failed to initialize.") # 检查是否生成了深度图 if depth_image is None: raise RuntimeError("Depth image was not generated.") # 将深度图转换为 numpy 数组 depth_map = np.asarray(depth_image) # 返回未归一化的深度图和最大深度值 max_depth = np.nanmax(depth_map) # 获取最大深度值 return depth_map, max_depth def load_camera_parameters(colmap_params_path): """ 从COLMAP参数文件加载相机参数。 参数: colmap_params_path (str): COLMAP参数文件的路径 返回: tuple: 包含相机参数列表、图像宽度和高度 """ images = read_images_text(f"{colmap_params_path}/images.txt") cameras = read_cameras_text(f"{colmap_params_path}/cameras.txt") camera_params = [] for image_id, image in images.items(): camera_id = image.camera_id camera = cameras[camera_id] # 读取内参 相机内参可以获取 fx, fy, cx, cy K = np.array( [ [camera.params[0], 0, camera.params[2]], [0, camera.params[1], camera.params[3]], [0, 0, 1], ] ) # 读取外参 相机外参可以获取 qvec 和 tvec R = image.qvec2rotmat() t = np.array(image.tvec) camera_params.append((image.name, K, R, t)) return camera_params, camera.width, camera.height def generate_depth_maps_and_save(mesh, camera_params, width, height, output_path): """ 生成深度图并保存为 .npy 格式。 注意：此函数保留用于向后兼容，建议使用 generate_depth_maps_and_save_optimized 以获得更好的性能 参数: mesh (o3d.geometry.TriangleMesh): 3D网格 camera_params (list): 相机参数列表 width (int): 图像宽度 height (int): 图像高度 output_path (str): 输出路径 返回: None """ # 调用优化版本 generate_depth_maps_and_save_optimized(mesh, camera_params, width, height, output_path) def create_depth_maps(mesh_path, colmap_params_path, output_path, use_optimized=True, max_workers=None): """ 创建深度图并保存为 .npz 格式。 参数: mesh_path (str): 3D网格文件路径 colmap_params_path (str): COLMAP参数文件路径 output_path (str): 输出路径 use_optimized (bool): 是否使用优化版本（默认True） max_workers (int, optional): 异步保存的最大工作线程数 返回: None """ print(f"加载3D网格: {mesh_path}") # 加载 3D 网格 mesh = o3d.io.read_triangle_mesh(mesh_path) if len(mesh.vertices) == 0: raise ValueError(f"无法加载网格文件或网格为空: {mesh_path}") print(f"加载相机参数: {colmap_params_path}") # 加载相机参数 camera_params, width, height = load_camera_parameters(colmap_params_path) print(f"找到 {len(camera_params)} 个相机参数") print(f"图像尺寸: {width} x {height}") # 使用优化版本生成并保存深度图 if use_optimized: generate_depth_maps_and_save_optimized(mesh, camera_params, width, height, output_path, max_workers) else: # 使用原始版本 for i, (name, K, R, t) in enumerate(camera_params): depth_map, max_depth = render_depth_map(mesh, K, R, t, width, height) # 保存深度图为 .npz 文件 depth_filename = f"{output_path}/{name.split('.')[0]}.npz" np.savez_compressed(depth_filename, depth=depth_map, max_depth=max_depth) if (i + 1) % 10 == 0: print(f"已处理 {i + 1}/{len(camera_params)} 张图片") # 示例用法 if __name__ == "__main__": parser = argparse.ArgumentParser( description="Generate depth maps from a mesh and colmap parameters" ) parser.add_argument("--mesh_path", type=str, required=True, help="Path to the mesh file") parser.add_argument( "--colmap_params_path", type=str, required=True, help="Path to the colmap parameters" ) parser.add_argument("--output_path", type=str, required=True, help="Path to the output directory") parser.add_argument( "--use_optimized", action="store_true", default=True, help="Use optimized version with renderer reuse and async I/O (default: True)" ) parser.add_argument( "--no_optimized", action="store_true", help="Use original version (slower)" ) parser.add_argument( "--max_workers", type=int, default=None, help="Maximum number of worker threads for async I/O (default: None, uses system default)" ) args = parser.parse_args() # 如果指定了 --no_optimized，则使用原始版本 use_optimized = not args.no_optimized import time start_time = time.time() print("=" * 50) print("深度图生成工具") print("=" * 50) print(f"网格文件: {args.mesh_path}") print(f"COLMAP参数路径: {args.colmap_params_path}") print(f"输出路径: {args.output_path}") print(f"使用优化版本: {use_optimized}") if use_optimized and args.max_workers: print(f"最大工作线程数: {args.max_workers}") print("=" * 50) try: create_depth_maps( args.mesh_path, args.colmap_params_path, args.output_path, use_optimized=use_optimized, max_workers=args.max_workers ) print(" 深度图生成完成！") except Exception as e: print(f" 生成深度图时出错: {e}") raise e elapsed_time = time.time() - start_time minutes = int(elapsed_time // 60) seconds = int(elapsed_time % 60) print(f" 深度图生成完成，用时: {minutes}分{seconds}秒")