Learning Plug-and-play Memory for Guiding Video Diffusion Models

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

Official PyTorch implementation of "GaussianLSS - Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting" (CVPR 2025).

Visual Geometry Transformer for Autonomous Driving

Joint 3D Geometry Reconstruction and Motion Generation for 4D Synthesis from a Single Image

Code release for https://wonderzoom.github.io/

Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

[ICCV 2025 ⭐highlight⭐] Implementation of VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

Learning to Drive via Real-World Simulation at Scale

[NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Three.js-based implementation of 3D Gaussian splatting

[NeurIPS 25] VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting

[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models

[ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes

[CVPR2025] Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

PhiGensis

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"

[NeurIPS 2025] ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

科学上网🕸️之跑路机场名单收集（2020-2025），欢迎投稿。Ad🔗🈲🙅❌

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

Dynamic 3D Foundation Model using Causal Transformer

[ICCV 2025] Driving Scene Synthesis on Free-form Trajectories with Generative Prior