An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Texas holdem OpenAi gym poker environment with reinforcement learning based on keras-rl. Includes virtual rendering and montecarlo for equity calculation.

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

[ICRA 2025] Persistent Object Gaussian Splat (POGS) for Tracking Human and Robot Manipulation of Irregularly Shaped Objects

Official repository of "CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement".

[NeurIPS 2025] This repo is official PyTorch implementation of the paper "Learning Dense Hand Contact Estimation from Imbalanced Data".

Denoising Diffusion Probabilistic Models

[RSS 2025] Gripper Keypose and Object Pointflow as Interfaces for Bimanual Robotic Manipulation

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

[ICCV 2021] CPF: Learning a Contact Potential Field to Model the Hand-Object Interaction

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

A collaboration friendly studio for NeRFs

(TPMAI 2025) Generalized Multi-view Hand Mesh Reconstruction

🤖 An Open Source Texas Hold'em AI

[CVPR'24] Group Anything with Radiance Fields

COLMAP - Structure-from-Motion and Multi-View Stereo

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Three.js-based implementation of 3D Gaussian splatting

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

[ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Pre-generated AprilTag images

DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies

[CoRL 24] GenDP: 3D Semantic Fields for Category-Level Generalizable Diffusion Policy

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

[CVPR 25] G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation