[NeurIPS 2024 Spotlight]"LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS", Zhiwen Fan, Kevin Wang, Kairun Wen, Zehao Zhu, Dejia Xu, Zhangyang Wang

[CVPR 2025] Towards In-the-wild 3D Plane Reconstruction from a Single Image

Code & data for ICCV2025 paper

Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D gam…

Next-Generation GNSS Processing Library(WIP)

Official implementation of Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer

Multi-State Constraint Kalman Filter for Monocular Visual-Inertial Navigation.

The best ChatGPT that $100 can buy.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"

This is a list of relevant papers for 3D Geometric Foundation Models and Applications.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

egui: an easy-to-use immediate mode GUI in Rust that runs on both web and native

🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.

Source code for ICCV 2025 paper "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases"

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

An open source implementation of CLIP.

A VR viewer for gaussian splatting models developped as native plugin for unity with the original CUDA rasterizer.

[CVPR 2025] Relative camera pose estimation and visual localization with Reloc3r

[ICCV 2025] Official Implementation of "Online Language Splatting"

Cross-platform lib for process and system monitoring in Python

Modular wrapper for using OptiX with PyTorch.

A simple state update rule to enhance length generalization for CUT3R

YOLOE: Real-Time Seeing Anything [ICCV 2025]

Official implementation of Continuous 3D Perception Model with Persistent State

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.