For megadepth dataset, zero-padding exists in images

Evaluate pairwise distances between two batches of feature vectors.

Restore the parameters stored with the `store` method. Useful to validate the model with EMA parameters without affecting the

:param bins: tensor of shape [N_rays, M+1], M is the number of bins :param weights: tensor of shape [N_rays, M] :param N_samples: number

shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir

shift pixel for super-resolution with different scale factors Args: x: WxHxC or WxH sf: scale factor upper_left: shift dir

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and

Save the current parameters for restoring later. Args: parameters: Iterable of `torch.nn.Parameter`; the parameters to be

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may be

Warp kpts0 from I0 to I1 with depth, K and Rt Also check covisibility and depth consistency. Depth is consistent if relative error < 0.2 (har

Apply classifier guidance Specify a guidance scale as either a scalar Or a schedule as a list of tuples t = 0->1 and scale, e.g.

Checks whether a given tensor does exists in the graph.

Copied from: https://github.com/numpy/numpy/blob/fb215c76967739268de71aa4bda55dd1b062bc2e/numpy/lib/format.py#L788-L886 Read from file-like

USM sharpening. borrowed from real-ESRGAN Input image: I; Blurry image: B. 1. K = I + weight * (I - B) 2. Mask = 1 if abs(I - B) > thresho

aggregate mutli-view features by compute their cost variance :param multiview_features: (num of voxels, num_of_views, c) :par

A context manager that will prevent any logging messages triggered during the body from being processed. :param highest_level: the maxim

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

generate an anisotropic Gaussian kernel Args: ksize : e.g., 15, kernel size theta : [0, pi], rotation angle range l1

Appends dimensions to the end of a tensor until it has target_dims dimensions. From https://github.com/crowsonkb/k-diffusion/blob/master/k_diffusi

Kai Zhang (github: https://github.com/cszn)

Create a 1D, 2D, or 3D average pooling module.

bgr version of rgb2ycbcr only_y: only return Y channel Input: uint8, [0, 255] float, [0, 1]

two dimensional cubic interpolation :param p: [B, N, 4, 4] :param x: [B, N] :param y: [B, N] :return: