Gaussian-Informed Continuum for Physical Property Identification and Simulation

WebGL 3D Gaussian Splat Viewer

A generative and self-guided robotic agent that endlessly propose and master new skills.

A family of lightweight multimodal models.

This is the official implement of A Controllable Emotion Voice Conversion Framework with Pre-trained Speech Representations

Ongoing research training gaussian splatting at scale by distributed system

PositionBasedDynamics is a library for the physically-based simulation of rigid bodies, deformable solids and fluids.

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

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

Official implementation of Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle

DSPy: The framework for programming—not prompting—language models

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Universal Scene Description

Utilities and examples for constructing scenes with the USD Python API

GRUtopia: Dream General Robots in a City at Scale

This code is a non-official 2DGS implementation including forward and backward process of 2DGS with cuda.

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

[CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

Unofficial implementation of "Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting", ECCV2024.

[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering

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

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.

[CVPR2024 Highlight] Editable Scene Simulation for Autonomous Driving via LLM-Agent Collaboration