首先需要搞清楚3DGS的数据类型要求是什么

3DGS/gaussian-splatting/scene/dataset_readers.py里面

sceneLoadTypeCallbacks = {
    "Colmap": readColmapSceneInfo,
    "Blender" : readNerfSyntheticInfo
}

 一个是colmap的场景读取一个是合成场景的数据读取。

先看colmap的场景：

def readColmapSceneInfo(path, images, eval, llffhold=8):
    try:
        cameras_extrinsic_file = os.path.join(path, "sparse/0", "images.bin")
        cameras_intrinsic_file = os.path.join(path, "sparse/0", "cameras.bin")
        cam_extrinsics = read_extrinsics_binary(cameras_extrinsic_file)
        cam_intrinsics = read_intrinsics_binary(cameras_intrinsic_file)
    except:
        cameras_extrinsic_file = os.path.join(path, "sparse/0", "images.txt")
        cameras_intrinsic_file = os.path.join(path, "sparse/0", "cameras.txt")
        cam_extrinsics = read_extrinsics_text(cameras_extrinsic_file)
        cam_intrinsics = read_intrinsics_text(cameras_intrinsic_file)

    reading_dir = "images" if images == None else images
    cam_infos_unsorted = readColmapCameras(cam_extrinsics=cam_extrinsics, cam_intrinsics=cam_intrinsics, images_folder=os.path.join(path, reading_dir))
    cam_infos = sorted(cam_infos_unsorted.copy(), key = lambda x : x.image_name)

    if eval:
        train_cam_infos = [c for idx, c in enumerate(cam_infos) if idx % llffhold != 0]
        test_cam_infos = [c for idx, c in enumerate(cam_infos) if idx % llffhold == 0]
    else:
        train_cam_infos = cam_infos
        test_cam_infos = []

    nerf_normalization = getNerfppNorm(train_cam_infos)
    # ply_path = os.path.join(path, "input.ply")
    # print(ply_path)
    ply_path = os.path.join(path, "sparse/0/points3D.ply")
    bin_path = os.path.join(path, "sparse/0/points3D.bin")
    txt_path = os.path.join(path, "sparse/0/points3D.txt")
    if not os.path.exists(ply_path):
        print("Converting point3d.bin to .ply, will happen only the first time you open the scene.")
        try:
            xyz, rgb, _ = read_points3D_binary(bin_path)
        except:
            xyz, rgb, _ = read_points3D_text(txt_path)
        storePly(ply_path, xyz, rgb)
    try:
        pcd = fetchPly(ply_path)
    except:
        pcd = None

    scene_info = SceneInfo(point_cloud=pcd,
                           train_cameras=train_cam_infos,
                           test_cameras=test_cam_infos,
                           nerf_normalization=nerf_normalization,
                           ply_path=ply_path)
    return scene_info

看看这个try expect是什么意思：可能发生错误的语句放在try模块里，用except来处理异常。也就是说，没有那些bin的时候可以用.txt替代。继续往下读。cam_infos_unsorted = readColmapCameras(cam_extrinsics=cam_extrinsics, cam_intrinsics=cam_intrinsics, images_folder=os.path.join(path, reading_dir))这里调用了上面的函数，往上看。

def readColmapCameras(cam_extrinsics, cam_intrinsics, images_folder):
    cam_infos = []
    for idx, key in enumerate(cam_extrinsics):
        sys.stdout.write('\r')
        # the exact output you're looking for:
        sys.stdout.write("Reading camera {}/{}".format(idx+1, len(cam_extrinsics)))
        sys.stdout.flush()

        extr = cam_extrinsics[key]
        intr = cam_intrinsics[extr.camera_id]
        height = intr.height
        width = intr.width

        uid = intr.id
        R = np.transpose(qvec2rotmat(extr.qvec))
        T = np.array(extr.tvec)

        if intr.model=="SIMPLE_PINHOLE":
            focal_length_x = intr.params[0]
            FovY = focal2fov(focal_length_x, height)
            FovX = focal2fov(focal_length_x, width)
        elif intr.model=="PINHOLE":
            focal_length_x = intr.params[0]
            focal_length_y = intr.params[1]
            FovY = focal2fov(focal_length_y, height)
            FovX = focal2fov(focal_length_x, width)
        else:
            assert False, "Colmap camera model not handled: only undistorted datasets (PINHOLE or SIMPLE_PINHOLE cameras) supported!"

        image_path = os.path.join(images_folder, os.path.basename(extr.name))
        image_name = os.path.basename(image_path).split(".")[0]
        image = Image.open(image_path)

        cam_info = CameraInfo(uid=uid, R=R, T=T, FovY=FovY, FovX=FovX, image=image,
                              image_path=image_path, image_name=image_name, width=width, height=height)
        cam_infos.append(cam_info)
    sys.stdout.write('\n')
    return cam_infos

class CameraInfo(NamedTuple):
    uid: int
    R: np.array
    T: np.array
    FovY: np.array
    FovX: np.array
    image: np.array
    image_path: str
    image_name: str
    width: int
    height: int



 cam_info = CameraInfo(uid=uid, R=R, T=T, FovY=FovY, FovX=FovX, 
        /image=image,mage_path=image_path, 
        /image_name=image_name, width=width, height=height)

基本上就是内参加外参了。intr.model影响着内参。

话说csdn为什么不给代码换行功能

看一下这个能不能用COLMAP已知相机内外参数重建稀疏/稠密模型 - thronsbird - 博客园 (cnblogs.com)

发现3DGS里面点云数据需要法向量

gaussian-splatting/scene/dataset_readers.py

def fetchPly(path):
    plydata = PlyData.read(path)
    vertices = plydata['vertex']
    positions = np.vstack([vertices['x'], vertices['y'], vertices['z']]).T
    colors = np.vstack([vertices['red'], vertices['green'], vertices['blue']]).T / 255.0
    normals = np.vstack([vertices['nx'], vertices['ny'], vertices['nz']]).T
    return BasicPointCloud(points=positions, colors=colors, normals=normals)

最后需要这样几个文件：

位姿（这个文件一定要按照给定的格式来）

点云（推荐cloudcompare对点云进行编辑）

相机内参文件

发现一个问题，我的原始位姿的坐标系和点云的坐标系是在同一个坐标系下，但是colmap的输入点云和位姿的坐标系是需要乘以一个旋转矩阵的。这里我是对位姿数据进行一个旋转矩阵的变换操作。也是用cloudcompare这个软件，但是我忘记旋转矩阵是什么了，下次再补充。

最后作为3DGS的输入进行重建。