Stars
Color correction using standard color cards.
Colour checker detection with Python
[NeurIPS 2025] Pixel-Perfect Depth
🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.
LichtFeld Studio: Where reality and the digital world blend.
Official repository for code and information related to the HumanOLAT dataset (ICCV 2025).
Code and Data for "Automatically 3D reconstruction of human body based on synchronized camera array" @ Lightstage based 3D Reconstruction
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
The dataset of the paper "Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos".
A Handy Extrinsic Calibration Tool for LiDAR-camera Systems.
A web-based 3D visualization tool for 3D computer vision.
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
Enjoy the magic of Diffusion models!
Official inference repo for FLUX.1 models
Code for CineScale, higher-resolution video generation based on Wan
[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking
CoTracker is a model for tracking any point (pixel) on a video.
High-resolution models for human tasks.
InteriorGS: 3D Gaussian Splatting Dataset of Semantically Labeled Indoor Scenes
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Self-correction photometric stereo for highlight & shadow free PMS
PyTorch code and models for the DINOv2 self-supervised learning method.
[ECCV '24] Compressing 3D Gaussian Splats by placing their parameters into a 2D grid with local smoothness
configuration files for new server setup