[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Cross-platform, customizable ML solutions for live and streaming media.

HaMeR: Reconstructing Hands in 3D with Transformers

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A command-line tool to generate GitHub and GitLab activity graph.

Pytorch code for ICRA'22 paper: "Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation"

Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

总结3D视觉所涉及到的边边角角知识点，包括VSLAM、点云后处理、相机标定、深度学习等。

PyTorch code and models for VJEPA2 self-supervised learning from video.

⏰ Collaboratively track worldwide conference deadlines (Website, Python Cli, Wechat Applet) / If you find it useful, please star this project, thanks~

A Modular Framework for 3D Generation and Beyond [WIP]

系统前端

Code for "OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models" NeurIPS 2022

[CVPR 2024] Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)

PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation

[CVPR2025] EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

[CVPR 2024] HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

A curated list of awesome awesomeness about artificial intelligence

[CVPR 2025] Any6D: Model-free 6D Pose Estimation of Novel Objects

[CVPR2024] Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".

Awesome work on object 6 DoF pose estimation

[CVPR 2024] PyTorch implementation of GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

一键安装程序，欢迎大家提交代码和小鱼一起一键安装停止浪费生命

PID controller following a moving carrot