GRUtopia: Dream General Robots in a City at Scale

Code&Data for Grounded 3D-LLM with Referent Tokens

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型

Official implementation of the paper "PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios" (CVPR 2024).

Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

[CVPR 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI

Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

[NeurIPS 2023] OV-PARTS: Towards Open-Vocabulary Part Segmentation

An Open-source Framework for Autonomous Language Agents

[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts

[ECCV 2024] PointLLM: Empowering Large Language Models to Understand Point Clouds

[ICCV 2023] GeoMIM: towards better 3d knowledge transfer via masked image modeling for multi-view 3d understanding

[ECCV 2024] DriveLM: Driving with Graph Visual Question Answering

A lightweight framework for building LLM-based agents

3D Occupancy Prediction Benchmark in Autonomous Driving

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

Official release of InternLM2.5 7B base and chat models. 1M context support

Official Code for DragGAN (SIGGRAPH 2023)

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

[ICCV 2023] OccNet: Scene as Occupancy

Multimodal-GPT

An open-source tool-augmented conversational language model from Fudan University

Topology Reasoning for Scene Perception in Autonomous Driving

[CoRL 2023] DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking

[IJCV 2024] P3Former: Position-Guided Point Cloud Panoptic Segmentation Transformer

[CVPR 2023] MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training

A collaboration friendly studio for NeRFs