Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

The Sky's the Limit: Relightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In Visibility

CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

GLOMAP - Global Structured-from-Motion Revisited

CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets

code for solving global structure from motion problem in the ECCV'14 paper "Robust Global Translations with 1DSfM"

Official implementation of the paper "HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting""

We extend Segment Anything to 3D perception by combining it with VoxelNeXt.

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

Code for "Object as Query: Lifting any 2D Object Detector to 3D Detection"

[CVPR2024] Official implementation of "RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception"

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.

[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

A unified framework for 3D content generation.

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

A collaboration friendly studio for NeRFs

A9 Dataset Development Kit

[ICLR'23 Spotlight & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

[CVPR 2022 Oral, Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

Code for MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection