Overlays text on given image. NOTE: The input image is assumed to be with `RGB` channel order. Args: image: The image to overlay tex

Parses an argument to boolean.

Create the data loader for the corresponding trainign set

Expects a two dimensional flow image of shape. Args: flow_uv (np.ndarray): Flow UV image of shape [H,W,2] clip_flow (float,

Encodes input xyz to warp field for points Inputs: x: (B, self.in_channels_xyz) the embedded vector of po

Embeds x to (x, sin(2^k x), cos(2^k x), ...) Different from the paper, "x" is also in the output See https://github.com/bmild

Embeds x to (x, sin(2^k x), cos(2^k x), ...) Different from the paper, "x" is also in the output See https://github.com/bmild

Embeds x to (x, sin(2^k x), cos(2^k x), ...) Different from the paper, "x" is also in the output See https://github.com/bmild

Encodes input (xyz+dir) to rgb+sigma (not ready to render yet). For rendering this ray, please see rendering.py Inputs:

Gets a blank image, either white of black. NOTE: This function will always return an image with `RGB` channel order for color image and pixel

Gets the shape of a grid based on the size. This function makes greatest effort on making the output grid square if neither `height` nor `wid

Post-processes image to pixel range [0, 255] with dtype `uint8`. This function is particularly used to handle the results produced by deep mo

Pre-processes image by adjusting the pixel range and to dtype `float32`. This function is particularly used to convert an image or a batch of ima

Saves an image to disk. NOTE: The input image (if colorful) is assumed to be with `RGB` channel order and pixel range [0, 255]. Args:

r""" Sets the epoch for this sampler. When :attr:`shuffle=True`, this ensures all replicas use a different random ordering for each ep