A generative world for general-purpose robotics & embodied AI learning.

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

田柯宇 (Tian Keyu)恶意攻击集群事件的证据揭露

Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"

Reproducible evaluation of NeRF and 3DGS methods

fast distance and ray intersection queries

[ECCV 2024] Code for VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models

Grounding Image Matching in 3D with MASt3R

CUDA accelerated rasterization of gaussian splatting

Dual-fisheye stitching

Official Implementation of ICLR'24: Kosmos-G: Generating Images in Context with Multimodal Large Language Models

The Lensfun project Git repository

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

DUSt3R: Geometric 3D Vision Made Easy

[CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

code for GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces

Tiny Gaussian Splatting Viewer

🛡️[ICLR'2024] Toward effective protection against diffusion-based mimicry through score distillation, a.k.a SDS-Attack

Concept Sliders for Precise Control of Diffusion Models

WebGPU rendering experiments

A library for differentiable nonlinear optimization

An open-source impl. of Large Reconstruction Models

My Modification to vanilla 3D Gaussians

Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".

Conversion between different conventions of camera matrices and transform matrices.

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

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

Official implementation of "LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching"