4DVLab

Vision-Centric-BEV-Perception. Vision-Centric BEV Perception: A Survey

DexGrasp-Anything. CVPR 2025(Highlight) DexGraspAnything: Towards Universal Robotic Dexterous Grasping with Physics Awareness

OctreeOcc. Official implement for paper "OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries"

STCrowd. Python

SemGeoMo. Official implement for SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance

RealDex. Python

LaserHuman. Official implement for LaserHuman.

HuCenLife. This is the official implement for Human-centric Scene Understanding in 3D Large-scale Scenarios.

IDKB. Official repository for paper "Can LVLMs Obtain a Driver’s License? A Benchmark Towards Reliable AGI for Autonomous Driving"

UniDemoire. Official repository for paper "UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis"

DexH2R. Python

CL3D. This repository is for CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection.

ResVLA. [ICML 2026] ResVLA: From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges

Freqpolicy. [NIPS 2025] FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

LiveHPS. This is the official implement for LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment.

LiveHPS2. This is the official implement for LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment.

LIP. This is the official implement for LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors.

EvolvingGrasp. ICCV 2025 EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment

FusionPose. This repository is for LiCamPose dataset and official implement for Weakly Supervised 3D Multi-person Pose Estimation for Large-scale Scenes based on Monocular Camera and Single LiDAR.

WildRefer. Python

ReMoGen. ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data

See_More_Know_More. Official implement for paper "See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data".

UniAfford. Python

GaussianShader. GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces