[CVPR 2026 Oral] "MARCO: Navigating the Unseen Space of Semantic Correspondence"

[CVPR 2026 Oral] "INSID3: Training-Free In-Context Segmentation with DINOv3"

Official Repository for "Communication Efficient Federated Learning with Generalized Heavy-Ball Momentum", accepted at TMLR 2025

[NeurIPS 2025 Spotlight] "SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation."

A curated list of awesome Visual Place Recognition papers

[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).

🚀 Lightning-fast computer vision models. Fine-tune SOTA models with just a few lines of code. Ready for cloud ☁️ and edge 📱 deployment.

pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…

[CVPR 2025 Highlight] "SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation"

Refine high-quality datasets and visual AI models

A beautiful, simple, clean, and responsive Jekyll theme for academics

Documentation that simply works

ROS drivers for joysticks