Compute the entire variational lower-bound, measured in bits-per-dim, as well as other related quantities. :param model: the

Creates a new camera for the center-cropped view

Get all of the supported channels available for the views. This can be arbitrary, but there are some standard names: "R", "G

Sample x_{t+1} from the model using DDIM reverse ODE.

Generate samples from the model using DDIM. Same usage as p_sample_loop().

:param batch: must contain either - rays: [batch_size x ... x 2 x 3] specify the origin and direction of each ray.

Predict an attribute given position

:param query: the points in the field to query. :param params: Meta parameters :param options: Optional hyperparameters

:param x: an [N x C x T] tensor. :param t: an [N] tensor. :return: an [N x C' x T] tensor.

:param x: an [N x C x T] tensor. :param t: an [N] tensor. :param images: a batch of images to condition on. :param te

:param x: an [N x C x T] tensor. :param t: an [N] tensor. :param images: a batch of images to condition on. :param em

:param x: an [N x C1 x T] tensor. :param t: an [N] tensor. :param low_res: an [N x C2 x T'] tensor of conditioning points.

:param x: an [N x C1 x T] tensor. :param t: an [N] tensor. :param low_res: an [N x C2 x T'] tensor of conditioning points.

:param x: an [N x C x T] tensor. :param t: an [N] tensor. :return: an [N x C' x T] tensor.

Generate a batch of embeddings from a mixture of images, texts, precomputed embeddings, and possibly empty values. For each

:param channels: [batch_shape, inner_batch_shape, n_channels, height, width] :param position: [batch_shape, inner_batch_shape, 3, hei

:param channels: [batch_shape, inner_batch_shape, n_channels, height, width] :param origin: [batch_shape, inner_batch_shape, 3, heigh

Input: xyz: input points position data, [B, C, N] points: input points data, [B, D, N] Return: ne

Input: xyz: input points position data, [B, C, N] points: input points data, [B, D, N] Return: ne

Input: xyz: input points position data, [B, C, N] points: input points data, [B, D, N] Return: ne

Input: xyz1: input points position data, [B, C, N] xyz2: sampled input points position data, [B, C, S] po

Encode a batch of data into a batch of latent information.

Transmit the batch through the encoder and then the renderer.

:return: a tuple of ( the initial output tokens of size [batch_size, data_ctx + latent_ctx, width], an iterator over

:return: a tuple of ( the initial output tokens of size [batch_size, data_ctx + latent_ctx, width], an iterator over