EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory

The best ChatGPT that $100 can buy.

Lightweight Stereo VIO

Fork of VGGT-Long with Colmap sparse model for Gaussian splatting

[NeurIPS 2025] Pixel-Perfect Depth

Visual Odometry with Transformers

A server, NAS navigation panel, Homepage, browser homepage. | 一个服务器、NAS导航面板、Homepage、浏览器首页。

OpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for everyone, forever f…

Official Implementation of DA^2: Depth Anything in Any Direction

Code for QuantVGGT: Quantized Visual Geometry Grounded Transformer

A simple state update rule to enhance length generalization for CUT3R

Benchmarking Visual-Inertial SLAM at City Scale (ICCV 2025).

A repository containing useful resources to learn Machine Learning Fundamentals

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

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

Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.

Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

[CoRL 2025] ActLoc: Learning to Localize on the Move via Active Viewpoint Selection

FlowR: Flowing from Sparse to Dense 3D Reconstructions (ICCV'25 Highlight)

🥢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.

Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and performing real-time speech generation.

VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Quadratic programming solvers in Python with a unified API

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations