Lists (1)
Stars
A Best-of-list of Robot Simulators, re-generated weekly on Wednesdays
[ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes
Release repo for our SLAM Handbook
Full python interactive 3D Gaussian Splatting viewer for real-time editing and analyzing.
[CVPR 2025 Highlight] Towards Autonomous Micromobility through Scalable Urban Simulation
Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset
[ArXiv 2025] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
[CVPR 2025 Best Paper Award Candidate] VGGT: Visual Geometry Grounded Transformer
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
Collect some World Models for Autonomous Driving (and Robotic) papers.
Original reference implementation of the CUDA rasterizer from the paper "StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Rendering"
This repository contains the Hugging Face Agents Course.
[NeurIPS 2024] Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
Official implementation of the paper "HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving"
Simple Waymo Open Dataset Reader
Reproducing Gaussian Splatting
[AAAI 2025] Offical implementation of "DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input"
Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence
(WIP) A small but powerful, homemade PyTorch from scratch.
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
Infinite Photorealistic Worlds using Procedural Generation
[CVPR 2025] GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data (CVPR 2025)
Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.