127 datasets found

DiffWave: A Versatile Diffusion Model for Audio Synthesis.

The dataset used in the paper is a stochastic optimal control problem, where the goal is to drive the behavior of a noisy system.

Shared autonomy is an operational concept in which a user and an autonomous agent collaboratively control a robotic system. It provides a number of advantages over the extremes...

Event skeleton generation, aiming to induce an event schema skeleton graph with abstracted event nodes and their temporal relations from a set of event instance graphs.

Synthetic data from diffusion models augmenting real-world data

The dataset used in the paper for 3D generation using TeT-Splatting.

InstructPix2Pix is a model for image editing tasks, including removing objects from images.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the DDIM diffusion model and the LDMs diffusion model.

DiffAssemble is a unified learning-based solution using diffusion models and graphs neural networks for reassembly tasks that achieve SOTA results in most 2D and 3D without...

The dataset used for text-to-image diffusion models, including Bluefire, Paintings, 3D, and Origami styles.

DiffRec, L-DiffRec, and T-DiffRec datasets.

Diffusion Recommender Model, which infers users’ interaction probabilities in a denoising manner.

The data distribution is taken to be a 25-dimensional Gaussian distribution, generated by mixture of gaussians.

The data distribution is taken to be a one-dimensional Gaussian distribution, P0(x0) = N (x0 | 0, v0).

A dataset of 121 video sequences of common household objects, captured by GoPro Hero9 action cameras at 30 FPS and 1920 × 1080 resolution.

The HPSv2 dataset is a text-image pair dataset containing 3200 prompts and their corresponding images.

The dataset used for the tabletop manipulation and two-car reach-avoid problems.

The dataset used in the paper is LSUN bedroom and church-outdoor datasets (64×64).

The dataset used in the paper for training and testing the Joint2Human model.

The dataset used in the paper for training and testing the Joint2Human model.