Stars
uniGradICON: A Foundation Model for Medical Image Registration (MICCAI 2024)
UNet Zoo: A PyTorch library for diverse UNet architectures, inspired by timm. Provides a unified API for easy model creation, training, and experimentation in image segmentation.
RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments (ICONIP19)
[ICCV 2025] Official repository of the paper "Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation"
Testing adaptation of the DINOv2/3 encoders for vision tasks with Low-Rank Adaptation (LoRA)
SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3
Official repository for Dino U-Net: Exploiting High-Fidelity Dense Features from Foundation Models for Medical Image Segmentation. (DINOv3)
Reference PyTorch implementation and models for DINOv3
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
Python package for signal processing, with emphasis on iterative methods
Official pytorch repository for "Diffusion Posterior Sampling for General Noisy Inverse Problems"
Materials for the ISMRM 2025 educational course "Surfing School Hands On Open Source MR" held on May 11, 2025
FreeU: Free Lunch in Diffusion U-Net (CVPR2024 Oral)
Reconstruction code and reproducible reconstruction scripts for DNLINV paper
Image restoration with neural networks but without learning.
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.
Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).
Open-source and strong foundation image recognition models.
👋 Xplique is a Neural Networks Explainability Toolbox