[CVPR 2025] VGGT: Visual Geometry Grounded Transformer

Instructions and utilities for use of EPFL's compute cluster.

[CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion

uniGradICON: A Foundation Model for Medical Image Registration (MICCAI 2024)

Techniques for deep learning with satellite & aerial imagery

the cross-modality MAS method

Advanced Normalization Tools (ANTs)

The Medical Image Registration ToolKit (MIRTK), the successor of the IRTK, contains common CMake build configuration files, core libraries, and basic command-line tools. Extension packages are host…

Cardiac Image Multi-Atlas Segmentation pipeline (CIMAS)

Deep learning framework for MRI reconstruction

Investigating CoT Reasoning in Autoregressive Image Generation

Official PyTorch implementation of the CVPR 2023 paper "Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models (https://arxiv.org/abs/2211.10655)"

Official Code Implementation for "Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing" (CVPR 2025))

[MICCAI 2024 Early Acceptance] Official Pytorch Code for Slice-Consistent 3D Volumetric Brain CT-to-MRI Translation with 2D Brownian Bridge Diffusion Model

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

A summary of related works about flow matching, stochastic interpolants

code for our ECCV 2020 spotlight paper "Multimodal Shape Completion via Conditional Generative Adversarial Networks"

Multilabel semantic segmentation for pelvic OAR structures

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

A public endoscopic video dataset for polyp detection

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.