Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten

r"""Masked mean `reduce_masked_mean(x, mask)` computes the mean of a tensor :attr:`input` over a mask :attr:`mask`, returning .. math::

Render the mesh. Args: mesh : meshmodel extrinsics (torch.Tensor): (4, 4) camera extrinsics intr

Resets the image embeddings and other state variables.

Remove all input points or mask in all frames throughout the video.

Run the pipeline. Args: image (Image.Image): The image prompt. num_samples (int): The number of samples to g

Prepares inputs and applies network 'fn'. @inputs: (N_ray,N_sample,3) sampled points on rays in GL camera's frame @viewdirs: (N_ray,3) unit le

@near: (N_ray,1)

Processes specialized tokens with shape (1, 2, X, C) for multi-frame processing: 1) Uses the first position (index=0) for the first frame onl

args: x: H W

Weighted Procrustes Analysis in PyTorch (batched). Args: X: (B, 1, N, 3), source point cloud. Y: (B, T, N, 3), target po

Multi-layer perceptron

Initialize ResidualBlock.

Split a multi-object output into per-object output slices and add them into `output_dict_per_obj`. The resulting slices share the sam

Applies 1D rotary position embeddings along one dimension. Args: tokens: Input token features. positions: Position in

Apply positional embedding to tensor x.

Apply positional embedding to tensor x.

Remove the non-conditioning memory around the input frame. When users provide correction clicks, the surrounding frames' non-conditio

Encode the current image and its prediction into a memory feature.

Forward SAM prompt encoders and mask heads. Inputs: - backbone_features: image features of [B, C, H, W] shape - poin

`maskmem_pos_enc` is the same across frames and objects, so we cache it as a constant in the inference session to reduce session stor

Initialize the image conditioning model.

Map client-side object id to model-side object index.

Positionally encode points that are normalized to [0,1].

Create a residual block.

Activate pose parameters with specified activation functions. Args: pred_pose_enc: Tensor containing encoded pose parameters [transl

Bake colors to mesh vertices from multiple observations using differential rasterization. Args: vertices (np.array): Vertices of the

Convert base64 string back to numpy array

Convert base64 string back to numpy array

Calculates boxes in XYXY format around masks. Return [0,0,0,0] for an empty mask. For input shape C1xC2x...xHxW, the output shape is C1xC2x..

r"""Sample a tensor using bilinear interpolation `bilinear_sampler(input, coords)` samples a tensor :attr:`input` at coordinates :attr:`coord

批量将深度图转换为点云。 参数： - depth_map: 深度图，形状为 (b, h, w)，每个样本的深度图。 - K: 相机内参矩阵，形状为 (b, 3, 3)，每个样本的相机内参。 - pose: 相机外参矩阵，形状为 (b, 4, 4)，

Computes the stability score for a batch of masks. The stability score is the IoU between the binary masks obtained by thresholding the p

Inverse to pose_encoding_to_camera