Repository for the paper "Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images"

A conditional version of the "very deep variational autoencoder" proposed by Rewon Child at OpenAI (2020)

Unpaired Image Translation, Neurips2022

Unpaired Image-to-Image Translation with Shortest Path Regularization

UVCGAN v2: An Improved Cycle-Consistent GAN for Unpaired Image-to-Image Translation

Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)

Image-to-Image Translation in PyTorch

A minimal example for training a flow matching model in a pretrained VAE's latent space to generate MNIST digits.

TorchCFM: a Conditional Flow Matching library

Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Segmentation models for 3D data with different backbones. PyTorch.

3D U-Net model for volumetric semantic segmentation written in pytorch

Master thesis for the MSc. Artificial Intelligence at the University of Amsterdam, 2019. Topic: Super-resolution with Conditional Normalizing Flows.

A Collection of Variational Autoencoders (VAE) in PyTorch.

A large-scale publicly-available visual-thermal-audio dataset designed to encourage research in the general areas of user authentication, facial recognition, speech recognition, and human-computer …

A new data augmentation method for extreme lighting conditions.

Kernel Stein Discrepancy Descent : a method to sample from unnormalized densities

Keypoint-Guided Optimal Transport (NeurIPS 2022)

Implementation for the paper "PatchNR: Learning from Very Few Images by Patch Normalizing Flow Regularization".

WPPNets and WPPFlows: The Power of Wasserstein Patch Priors for Superresolution.