Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

Reuse your features: unifying retrieval and feature-metric alignment (ICRA 2023)

Code and models for MICCAI23 paper: "Self-Supervised Learning for Endoscopy Video Analysis".

Any-Feature V-SLAM is an automated visual SLAM library for Monocular cameras capable of switching to a chosen type of feature effortlessly and without manual intervention.

A Python library for explainable AI using approximate reasoning

Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.

Optimal Transport Aggregation for Visual Place Recognition

Minimal solvers for calibrated camera pose estimation

Pytorch Implementation of Unifying Deep Local and Global Features for Image Search (DELG)

Official PyTorch Implementation of Correlation Verification for Image Retrieval, CVPR 2022 (Oral Presentation)

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

[MICCAI'23] Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train

Training library for local feature detection and matching

Pytorch version of SfmLearner from Tinghui Zhou et al.

Colonoscopy 3D Video Dataset (C3VD) acquired with a high definition clinical colonoscope and high-fidelity colon models for benchmarking computer vision methods in colonoscopy.

QuadTree Attention for Vision Transformers (ICLR2022)

PyTorch Implementation of the ICCV 2023 paper: Generalized Differentiable RANSAC ($\nabla$-RANSAC).

Official repository for R2Former: Unified Retrieval and Reranking Transformer for Place Recognition

Official code for CVPR 2022 (Oral) paper "Deep Visual Geo-localization Benchmark"

Official Repository of "Learning Sequential Descriptors for Sequence-based Visual Place Recognition "

MixVPR: Feature Mixing for Visual Place Recognition (WACV 2023)

Navigation agent with Bayesian relational memory in the House3D environment

Official code for CVPR 2022 paper "Rethinking Visual Geo-localization for Large-Scale Applications"

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

A technical report on convolution arithmetic in the context of deep learning

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO