Create a unique temporary directory for each user session

Create a unique temporary directory for each user session

Create a normalized UV grid of shape (width, height, 2). The grid spans horizontally and vertically according to an aspect ratio, ensuri

Create a normalized UV grid of shape (width, height, 2). The grid spans horizontally and vertically according to an aspect ratio, ensuri

Create and load a VIT backbone module. Args: ---- preset: The VIT preset to load the pre-defined config. use_pretrained: Load

Args: cubes [Vx8] verts index for each cube value [Vx8xM] value to be scattered Operation: reduced[cubes[i][j]][k] +=

Args: cubes [Vx8] verts index for each cube value [Vx8xM] value to be scattered Operation: reduced[cubes[i][j]][k] +=

Deletes all invisible objects in the scene. Returns: None

Reverses the imagenet normalization applied to the input. Args: x (torch.Tensor - shape(N,3,H,W)): input tensor Returns: tor

args: xy_depth: [S H W 3] focal_length: [S] R: [S 3 3] W2C T: [S 3] W2C return: xyz: [S 3 (H W)

Apply depth of field effect to an image. Args: img (numpy.ndarray): (H, W, 3) input image. depth (numpy.ndarray): (H, W) dep

Convert a depth map to camera coordinates. Args: depth_map (np.ndarray): Depth map of shape (H, W). intrinsic (np.ndarray):

Convert a depth map to world coordinates. Args: depth_map (np.ndarray): Depth map of shape (H, W). intrinsic (np.ndarray): C

Apply disk blur to an image using FFT convolution. Args: image (np.ndarray): Input image, can be grayscale or color. radius

Apply disk blur to an image using FFT convolution. Args: image (np.ndarray): Input image, can be grayscale or color. radius

Generate disk kernel with given radius. Args: radius (int): Radius of the disk (in pixels). Returns: np.ndarray

Generate disk kernel with given radius. Args: radius (int): Radius of the disk (in pixels). Returns: np.ndarray

@K: 相机内参矩阵 (3, 3) @img: RGB 图像 (H, W, 3) @depth: 深度图 (H, W), dtype=np.float32 或类似 @ob_in_cam: 从物体坐标系到相机坐标系的变换矩阵 (4, 4) @bbox: (2,

绘制XYZ坐标轴，并更新深度图上的相应位置。 @color: 输入图像（BGR格式） @depth: 深度图 @ob_in_cam: 物体到相机的变换矩阵 @scale: 坐标轴长度比例 @K: 相机内参矩阵 @thickness: 线宽

Calculate edge recall for image matting. Args: ---- pr (np.ndarray): Predicted depth matrix. gt (np.ndarray): Ground truth bi

Used for Pose Refinement. Given the object's two poses in camera, convert them to relative poses in camera's egocentric view @A_in_cam: (B,4,4) torc

Evaluate spherical harmonics at unit directions using hardcoded SH polynomials. Works with torch/np/jnp. ... Can be 0 or more batch d

Return exif information as a dictionary. Args: ---- img_pil: A Pillow image. Returns: ------- A dictionary with extr

@A: (B*L,C,H,W) L is num of pairs

Extract first frame from video file

Extract first frame from video file

Extract a GLB file from the 3D model. Args: state (dict): The state of the generated 3D model. mesh_simplify (float): The me

Convert camera extrinsics and intrinsics to a compact pose encoding. This function transforms camera parameters into a unified pose encoding form

Find foreground-background relations between neighboring pixels in binary masks. Args: ---- d (np.ndarray): Binary depth matrix.

Find foreground-background relations between neighboring pixels with Non-Maximum Suppression. Args: ---- d (np.ndarray): Depth matrix

A post processor to fill small holes in mask scores with area under `max_area`.

Transform so that the first camera is the origin

make sure the poses in on window are normalized by the first frame, where the first frame transformation is the Identity Matrix. NOTE: P

Flattens a nested dictionary into a single-level dictionary, with keys as tuples.

Flattens a nested dictionary into a single-level dictionary, with keys as tuples.

Decode by projection and fusion of multi-resolution encodings. Args: ---- x (torch.Tensor): Input image. Returns

forward the video camera model, which predict ( `intr` `camera poses` `video depth` ) args: x: t

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

x_list contains a list of tensors to nest together and run

@x: embedded positions

Convert a focal length given in mm (35mm film equivalent) to pixels.

Gather the data from the leaf children. Args: data (torch.Tensor): the data to gather. The first dimension should be the

Gather the data from the leaf children. Args: data (torch.Tensor): the data to gather. The first dimension should be the

Gather the data from the non-leaf children. Args: data (torch.Tensor): the data to gather. The first dimension should be

Gather the data from the non-leaf children. Args: data (torch.Tensor): the data to gather. The first dimension should be

Generate 3D model and preview video from input image.

Generates a list of crop boxes of different sizes. Each layer has (2**i)**2 boxes for the ith layer.

根据分割掩码和深度图生成最终mask，并保存到指定路径。 :param seg_path: 分割掩码路径 :param depth_path: 深度图路径 :param out_path: 输出文件夹路径 :param area_threshold: 连通域

Generates a stable mask with a fewer number of coherent blocks.

@scene_pts: torch tensor (N,3)