RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments

A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.

Code of "OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments".

3D visualization of scientific data in Python

Offical PyTorch implementation of "BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework"

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

[ECCV 2024] 3D World Model for Autonomous Driving

[ECCV 2024] Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction

[RA-L 2024] GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping

DUSt3R: Geometric 3D Vision Made Easy

Depth Any Video with Scalable Synthetic Data (ICLR 2025)

DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

Repo for the papers "Intrinsic Image Decomposition via Ordinal Shading" (TOG 2023) and "Colorful Diffuse Intrinsic Image Decomposition in the Wild" (TOG 2024)

StableDelight: Revealing Hidden Textures by Removing Specular Reflections

The Gaussian Splatting Toolkit is a cutting-edge collection of tools designed for new view synthesis using Gaussian splatting techniques, providing a novel explicit 3D representation for scene rend…

[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

Datasets, Transforms and Models specific to Computer Vision

Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)

A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience

A Unified Framework for Surface Reconstruction

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Source code of paper "N3-Mapping: Normal Guided Neural Non-Projective Signed Distance Fields for Large-scale 3D Mapping"

A collaboration friendly studio for NeRFs

Demo code for GACE: Geometry Aware Confidence Enhancement

[ACM MM 2023] Official implementation of DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception