-
GeLaTO: Generative Latent Textured Objects
A compact representation that combines a set of coarse shape proxies with learned neural textures to encode both medium and fine scale geometry as well as view-dependent... -
Toy 2D dataset
The dataset used in the paper is a toy dataset consisting of 2D images. -
Anime128x128 dataset
The dataset used in the paper is a Anime128x128 dataset. -
CelebA128x128 dataset
The dataset used in the paper is a CelebA128x128 dataset. -
MNIST, CIFAR10, and CelebA datasets
The dataset used in the paper is a MNIST dataset, a CIFAR10 dataset, and a CelebA dataset. -
Optimal Transport Modeling
The dataset used in the paper is a noise distribution and a high-dimensional data distribution. -
Generative Adversarial Nets
Generative adversarial nets (GANs) are a class of deep learning models that consist of two neural networks: a generator and a discriminator. -
Two-dimensional mixture of Gaussians
The dataset used in the paper is a two-dimensional mixture of Gaussians. -
Denoising diffusion probabilistic models
Diffusion models currently stand as the predominant approach to generative modeling in audio and image domains. -
Promoter Design
We use the promoter DNA sequence dataset containing 100k promoter sequences with the corresponding transcription initiation signal profiles. -
Statistical Flow Matching
We apply SFM to diverse downstream discrete generation tasks across different domains including computer vision, natural language processing, and bioinformatics to demonstrate... -
Turbulent Flow Dataset
The dataset for the experiments comes from two dimensional turbulent flow simulated using the Lattice Boltzmann Method. The dataset consists of 1500 images of velocity fields,... -
Binarized MNIST
We use the preprocessed binarized MNIST dataset from [49] which has a split of 50k/10k/10k. -
Population Synthesis dataset
Dataset used for population synthesis and generative modeling. -
Particle Denoising Diffusion Sampler
Denoising diffusion models have become ubiquitous for generative modeling. The core idea is to transport the data distribution to a Gaussian by using a diffusion. Approximate...
