General-purpose computer vision framework merging YOLO detection, DINO foundation models, and Parameter-Efficient Fine-Tuning (PEFT).

We write your reusable computer vision tools. 💜

A procedural Blender pipeline for photorealistic training image generation

Masked Depth Modeling for Spatial Perception

CoSMo3D: Open-World Promptable 3D Semantic Segmentation through LLM-Guided Canonical Spatial Modeling (CVPR oral 2026)

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

[CVPR 2026 Highlight🎉] Official implementation of WorldForge

[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

[NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

The sources codes of BIT.

[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

[ICCV 2023] SurroundOcc: Multi-camera 3D Occupancy Prediction for Autonomous Driving

Code for 3D-LLM: Injecting the 3D World into Large Language Models

[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

A fast and simple method for multi-planes detection from point cloud

RGBD plane detection and color-based plane refinement

歌曲下载

一款 支持从百度、网易、qq、酷狗、咪咕等音乐网站搜索并下载歌曲的程序，支持下载无损音乐

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

插件化、定制化、无广告的免费音乐播放器

Android Music Player

A collection of design patterns/idioms in Python

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

A professionally curated list of awesome resources (paper, code, data, etc.) on transformers in time series.

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

Region-based Object Tracking

Transformer: PyTorch Implementation of "Attention Is All You Need"

CoTracker is a model for tracking any point (pixel) on a video.

Developer-first error tracking and performance monitoring