Stars
Octree-based 3D Convolutional Neural Networks
ROS Wrapper for Intel(R) RealSense(TM) Cameras
[Lumina Embodied AI Community] 具身智能技术指南 Embodied-AI-Guide
NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
[CVPR 2025] Online Video Understanding: OVBench and VideoChat-Online
The simplest, fastest repository for training/finetuning small-sized VLMs.
EyeTrax – webcam-based eye tracking made simple
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R
PointPWC-Net is a deep coarse-to-fine network designed for 3D scene flow estimation from 3D point clouds.
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
[CVPR'25] LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
🔥 The free & Open Source DocuSign alternative
A high-throughput and memory-efficient inference and serving engine for LLMs
EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular Video (ICRA2025)
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation for Indoor Scene.
A simple training-free approach adapting DUSt3R for dynamic scenes.
Wan: Open and Advanced Large-Scale Video Generative Models
[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".
[CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
[ICIP2023] TR3D: Towards Real-Time Indoor 3D Object Detection
[AAAI2025] UniDet3D: Multi-dataset Indoor 3D Object Detection
[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation