Sample x_{t-1} from the model at the given timestep. :param model: the model to sample from. :param x: the current tensor at

Predict the SDF at the query points given the encoded point clouds. Each query point should be treated independently, only condition

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of dif

Input: npoint: radius: nsample: xyz: input points position data, [B, N, 3] points: input points data, [B,

Input: xyz: input points position data, [B, N, 3] points: input points data, [B, N, D] Return: new_xyz: sampled point

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portio

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

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

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

Get a reasonable default number of query points for the model. In some cases, this might be the only supported size.

Sample a subset of the point cloud that is evenly distributed in space. First, a random point is selected. Then each successive poin

For a stream of point cloud batches, compute feature vectors and class predictions. :param point_clouds: a streamer for a sa

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

Predict the SDF at the coordinates x, given a batch of point clouds. Either point_clouds or encoded should be passed. Only exactly o

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