Official Implementation of Self-Supervised Street Gaussians for Autonomous Driving

Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation

An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.

[ICLR 2024] Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

[ICLR 2025] Autoregressive Video Generation without Vector Quantization

Code release for https://kovenyu.com/WonderWorld/

[AAAI 2025] DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation

A 3DGS framework for omni urban scene reconstruction and simulation.

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

[NeurIPS'2024]: DiffGS: Functional Gaussian Splatting Diffusion

Pytorch implementation of vid2vid for the CARLA simulator.

Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction

GaussianAD: Gaussian-Centric End-to-End Autonomous Driving

You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

Doe-1: Closed-Loop Autonomous Driving with Large World Model

Large Driving Models

Driving in the Occupancy World: Vision-Centric 4D Occupancy Forecasting and Planning via World Models for Autonomous Driving (AAAI-25)

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

Official implementation of the paper "HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving"

Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model

[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies

[ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale Occupancy Generation from Dynamic Scenes"

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

[NeurIPS 2024] Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving