🌍 WorldGen - Generate Any 3D Scene in Seconds

Towards a Generative 3D World Engine for Embodied Intelligence

[BMVC 2025] Occam’s LGS: An Efficient Approach for Language Gaussian Splatting

Blender addon for Depth-Anything-3 3D reconstruction

[NeurIPS 2025 Spotlight] ReSim: Reliable World Simulation for Autonomous Driving

Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

Large Driving Models

[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

Official implementation of “4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models” (CVPR 2025)

Official implementation of “4D LangVGGT: 4D Language-Visual Geometry Grounded Transformer”

Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]

A Python package for the TartanAir-V2 dataset.

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

A large-scale benchmark and learning environment.

RoboTwin 2.0 Offical Repo

A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

[ICCV 2023 Oral] ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

CUDA accelerated rasterization of gaussian splatting

3D Gaussian Splat Editor

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

Official Implementation of "Dens3R: A Foundation Model for 3D Geometry Prediction"

DUSt3R: Geometric 3D Vision Made Easy

Code of π^3: Permutation-Equivariant Visual Geometry Learning

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Code for "Improving Robotic Manipulation with Efficient Geometry-Aware Vision Encoder"