Stars
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.
Event-based Fusion for Motion Deblurring with Cross-modal Attention (ECCV'22 Oral) https://ahupujr.github.io/EFNet/
A contact solver for physics-based simulations involving 👚 shells, 🪵 solids and 🪢 rods.
Hiera: A fast, powerful, and simple hierarchical vision transformer.
Neural Network Compression Framework for enhanced OpenVINO™ inference
A library for performing proximity queries on a pair of geometric models composed of triangles
Zero to (https://)Myapp. Using Flask, Gunicorn, Nginx, and Certbot.
Official repository for "AM-RADIO: Reduce All Domains Into One"
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
JavaScript API for Chrome and Firefox
Easy to maintain open source documentation websites.
[ICCV 2023] MOSE: A New Dataset for Video Object Segmentation in Complex Scenes
BoT-SORT: Robust Associations Multi-Pedestrian Tracking
An open-source AI agent that brings the power of Gemini directly into your terminal.
Fine-tune Segment-Anything Model with Lightning Fabric.
Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"
Code for 'Stereo R-CNN based 3D Object Detection for Autonomous Driving' (CVPR 2019)
Object detection, 3D detection, and pose estimation using center point detection:
Get up and running with SAM, EfficientSAM, YOLO-World, and other promptable vision models locally.
Distributed code review system for Git repos
(ICCVW2025) Learning-based Event-Inertial Odometry
A simple HTML visualization tool for computer vision research 🛠️