diff --git a/build.sh b/build.sh
index e07172e..13cda81 100755
--- a/build.sh
+++ b/build.sh
@@ -12,7 +12,7 @@ function sudo_auth(){
 }
 
 function install_openmvs(){
-	cmake -S . -B make -DCMAKE_BUILD_TYPE=Release -DVCG_ROOT=./vcglib -DCGAL_DATA_DIR=/usr/share/cgal
+	cmake -S . -B make -DCMAKE_BUILD_TYPE=Release -DVCG_ROOT=./vcglib -DCGAL_DATA_DIR=/usr/share/cgal -DCMAKE_SKIP_RPATH=ON -DCMAKE_IGNORE_PATH=/root/miniconda3
 	cd make && make -j$(nproc)
 	make install
 }
diff --git a/libs/MVS/SceneTexture.cpp b/libs/MVS/SceneTexture.cpp
index f2edca7..02935e1 100644
--- a/libs/MVS/SceneTexture.cpp
+++ b/libs/MVS/SceneTexture.cpp
@@ -42,6 +42,9 @@
 #include "ConfigEnv.h"
 #include "cuda/MeshTextureCUDA.h"
 #include <sstream>
+#include <filesystem>
+
+namespace fs = std::filesystem;
 
 // namespace py = pybind11;
 
@@ -9589,12 +9592,13 @@ bool Scene::TextureMesh(unsigned nResolutionLevel, unsigned nMinResolution, unsi
 	printf("id=%s\n", id.c_str());
 
 #ifdef MASK_FACE_OCCLUSION
-	std::string basePath = "";
-	size_t lastSlash = baseFileName.find_last_of('/');
-    size_t secondLastSlash = baseFileName.find_last_of('/', lastSlash - 1);
-    if (secondLastSlash == std::string::npos) 
-        basePath = baseFileName;
-    basePath =  baseFileName.substr(0, secondLastSlash + 1);
+    fs::path p(baseFileName.c_str());
+    // 2. 获取父路径 (e.g., /path/to/data/scene)
+    fs::path parent = p.parent_path();
+    
+    // 4. 转换为字符串，并附加一个路径分隔符
+    //    ( / "" 会自动处理，确保 /path/to/data 变为 /path/to/data/ )
+    std::string basePath = (parent / "").string();
 
 	// printf("basePath=%s\n", basePath.c_str());
 
diff --git a/libs/MVS/mask_face_occlusion.py b/libs/MVS/mask_face_occlusion.py
index 0af59e8..9bfba79 100755
--- a/libs/MVS/mask_face_occlusion.py
+++ b/libs/MVS/mask_face_occlusion.py
@@ -6,7 +6,7 @@ from scipy.spatial.transform import Rotation
 import sys
 sys.path.append("/home/algo/Documents/openMVS/openMVS/libs/MVS/utils")
 from colmap_loader import read_cameras_text, read_images_text, read_int_text, write_int_text, read_indices_from_file
-from get_pose_matrix import get_w2c
+# from get_pose_matrix import get_w2c
 import argparse
 import matplotlib.pyplot as plt
 import collections
@@ -17,6 +17,985 @@ from torch.utils.dlpack import to_dlpack, from_dlpack
 import os
 from typing import Dict, List, Set
 
+#
+# 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_int_text(path):
+    dict_int = {}
+    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()
+                elem = int(elems[0])
+                dict_int[elem] = elem
+    return dict_int
+
+def read_indices_from_file(file_path):
+    indices_to_select = []
+    with open(file_path, 'r') as f:
+        for line in f:
+            index = int(line.strip())  # 读取每一行并转换为整数
+            indices_to_select.append(index)
+    return indices_to_select
+
+def write_int_text(list, path):
+    print("len(list)=", len(list))
+    if len(list) == 0:
+        return
+
+    with open(path, "w") as fid:
+        for item in list:
+            # print(item)
+            fid.write(str(item)+ "\n")
+
+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
+
+
+'''
+获取pose矩阵
+
+required:
+    - numpy
+'''
+
+import numpy as np
+from scipy.spatial.transform import Rotation
+
+def qvec2rotmat(qvec):
+    '''将四元数转换为旋转矩阵
+
+    Args:
+        qvec: 四元数
+
+    Returns:
+        旋转矩阵
+    '''
+    return Rotation.from_quat([qvec[1], qvec[2], qvec[3], qvec[0]]).as_matrix()
+    """
+    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 get_w2c(qvec: list, tvec: list) -> np.ndarray:
+    '''获取世界坐标系到相机坐标系的变换矩阵
+
+    Args:
+        qvec: 四元数
+        tvec: 平移向量
+
+    Returns:
+        世界坐标系到相机坐标系的变换矩阵
+    '''
+    #"""
+    w2c = np.eye(4).astype(np.float64)
+    w2c[:3, :3] = qvec2rotmat(qvec)
+    w2c[:3, 3] = tvec
+    #"""    
+    """
+    R = qvec2rotmat(qvec)  # 相机到世界的旋转
+    R_w2c = R.T                 # 世界到相机的旋转
+    t_w2c = -R_w2c @ tvec       # 平移分量
+
+    w2c = np.eye(4)
+    w2c[:3, :3] = R_w2c
+    w2c[:3, 3] = t_w2c
+    #"""
+    """
+    R2 = Rotation.from_quat([qvec[0], qvec[1], qvec[2], qvec[3]]).as_matrix()
+    # w2c = [R | -R @ tvec]
+    w2c2 = np.eye(4)
+    w2c2[:3, :3] = R2
+    w2c2[:3, 3] = -R2 @ tvec
+    print("w2c", w2c)
+    print("w2c2", w2c2)
+    #"""
+    """
+    w2c = np.eye(4).astype(np.float64)
+    R = qvec2rotmat(qvec)
+    w2c[:3, :3] = R.T
+    w2c[:3, 3] = -R @ tvec
+    #"""
+    """
+    w2c = np.eye(4).astype(np.float64)
+    R = Rotation.from_quat([qvec[1], qvec[2], qvec[3], qvec[0]]).as_matrix()
+    # COLMAP的tvec是相机在世界坐标系中的位置，需取反
+    t = -R.T @ tvec
+    w2c = np.eye(4)
+    w2c[:3, :3] = R.T  # 旋转部分
+    w2c[:3, 3] = t     # 平移部分
+    #"""
+    return w2c
+
+def get_c2w(qvec: list, tvec: list) -> np.ndarray:
+    '''获取相机坐标系到世界坐标系的变换矩阵
+
+    Args:
+        qvec: 四元数
+        tvec: 平移向量
+
+    Returns:
+        相机坐标系到世界坐标系的变换矩阵
+    '''
+    c2w = np.eye(4).astype(np.float64)
+    c2w[:3, :3] = qvec2rotmat(qvec).T
+    c2w[:3, 3] = -qvec2rotmat(qvec).T @ tvec
+    return c2w
+
 class ModelProcessor:
     def __init__(self):
 
@@ -1220,7 +2199,7 @@ class ModelProcessor:
         
         # 保存 visible_faces_map
         try:
-            with open(base_path + "_visible_faces_map.txt", "w", encoding='utf-8') as map_file:
+            with open(base_path + "/_visible_faces_map.txt", "w", encoding='utf-8') as map_file:
                 for image_name, face_set in visible_faces_map.items():
                     # 写入图像名称和所有面ID，用空格分隔
                     line = image_name + " " + " ".join(str(face) for face in face_set) + "\n"
@@ -1230,7 +2209,7 @@ class ModelProcessor:
         
         # 保存 face_visible_relative
         try:
-            with open(base_path + "_face_visible_relative.txt", "w", encoding='utf-8') as relative_file:
+            with open(base_path + "/_face_visible_relative.txt", "w", encoding='utf-8') as relative_file:
                 for face in face_visible_relative:
                     relative_file.write(str(face) + "\n")
         except IOError as e:
@@ -1238,7 +2217,7 @@ class ModelProcessor:
         
         # 保存 edge_faces_map
         try:
-            with open(base_path + "_edge_faces_map.txt", "w", encoding='utf-8') as map_file2:
+            with open(base_path + "/_edge_faces_map.txt", "w", encoding='utf-8') as map_file2:
                 for image_name, face_set in edge_faces_map.items():
                     line = image_name + " " + " ".join(str(face) for face in face_set) + "\n"
                     map_file2.write(line)
@@ -1247,7 +2226,7 @@ class ModelProcessor:
         
         # 保存 delete_edge_faces_map
         try:
-            with open(base_path + "_delete_edge_faces_map.txt", "w", encoding='utf-8') as map_file3:
+            with open(base_path + "/_delete_edge_faces_map.txt", "w", encoding='utf-8') as map_file3:
                 for image_name, face_set in delete_edge_faces_map.items():
                     line = image_name + " " + " ".join(str(face) for face in face_set) + "\n"
                     map_file3.write(line)