Stars
[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control
COLMAP - Structure-from-Motion and Multi-View Stereo
NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images
Automatic Workspace Calibration Using Homography for Pick and Place - IEEE CASE 2023, Auckland, New Zealand | DOI: 10.1109/CASE56687.2023.10260601
Implementation of the PointLIO algorithm on ROS2, compatible with most common LiDAR models
[NeurIPS'24] WildGaussians: 3D Gaussian Splatting In the Wild
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
pySLAM is a Python-based Visual SLAM pipeline that supports monocular, stereo, and RGB-D cameras. It offers a wide range of modern local and global features, multiple loop-closing strategies, a vol…
Source code for NeurIPS paper "POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images"
Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.
A bunch of scripts helping with daily tasks in 3D vision research.
Distribute and run LLMs with a single file.
Reproducible evaluation of NeRF and 3DGS methods
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
A collaboration friendly studio for NeRFs
Instant neural graphics primitives: lightning fast NeRF and more
A Unified Framework for Surface Reconstruction
Recent papers about generalizable 6DoF object pose estimation.
Awesome work on object 6 DoF pose estimation
This repository summarizes papers and codes for 6D Object Pose Estimation.