Computer Vision

Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.

A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations.

基于 PatchCore 的工业异常检测项目，研究 layer2/layer3 分数融合、敏感性引导收缩与风险受控门控，并提供 Streamlit 工程化 Demo。

Cornelius, le cadre/miroir intelligent : il vous reconnaît, vous écoute et répond en français. Assistant vocal, reconnaissance faciale en local, Home Assistant, météo, transports et beaucoup plus !

Seamless tetrahedral world map with a multi-stop flight trip planner in 9 languages. Also unfolds 360° photos for AI vision and drone attitude. 四面體世界地圖與出差航線規劃。

Record a sky camera around the clock, keep the footage on your own disk, and find what flew past.

Move hints for Tartarus Prison in Torchlight: Infinite: an overlay that reads the screen and the game's log and solves the board

Turn your cameras into Home Assistant sensors with a local AI: garage door open/closed, people and cars, water, gas and power meters read by any camera or ESP32-CAM. 100% local, any CPU.

Any3R: Feedforward 3D Reconstruction from Any Camera Type — pinhole, fisheye beyond 180°, 360° panoramas, or any mix, in one forward pass

🎬 Autonomous AI Studio for Manhwa & Webtoon Recaps — Vision Pipeline (YOLOv8 + Magi v2), Multi-Voice TTS & Video Synthesis

Personal project: where shoppers look, estimated from an ordinary security camera and open source AI (YOLO11, Gaze-LLE, Depth Anything V2)

Agent skill: outline, mask and count objects in photos with Meta's SAM 3 on your own NVIDIA GPU, with review, exports and a viewer. Works with Claude Code, Codex, Cursor, Pi and other Agent Skills clients.

A 4B diffusion grounding model for fast, precise visual evidence extraction. Unifies diverse grounding tasks through parallel decoding, with optional self-speculative decoding delivering 4.51x autoregressive throughput on COCO.

Your real-life buddy duck: an open-source embodied AI robot duck that walks, hears, sees, and has a life of its own. 让 DuckBuddy 成为你真正的生活伙伴鸭：开源具身智能小鸭机器人，运动、语音、视觉与生命层全部跑在机器人自己身上。Feetech servos + Orange Pi Zero 3W, built on Pollen Robotics' Microduck (unofficial).

Agent Skill for 15–90 s motion graphics, promo and character videos: reference analysis, seven stage gates, Remotion and HyperFrames engines.

冒险岛怀旧服（国服）自动练级工具 · 基于计算机视觉，免安装包解压即用（普通用户请看 README_用户版）

A fan-made, open-source recreation of The Machine from Person of Interest — MPOV on your own cameras, plus the console. With deep thanks to POI.

I gave Claude Code 120 pages of my handwritten college notes. It gave me back my handwriting as a real font, in 66 minutes for $13.68.

A laser dry-fire shooting game: your matte monitor is the target, an ordinary webcam watches it from the side, and your laser trainer leaves bullet holes where you hit.

Eyes are All JEV Needs - real time visual devisions from RGB, video and RGB-D cameras.

Windows Auto Clicker & Mouse/Keyboard Macro Recorder with Image Recognition | 鼠标自动连点、键鼠录制回放、图像识别找图点击

A desktop-native Windows system tray Telegram bot that monitors AniList for new anime announcements and releases with network auto-recovery, single-instance protection, and zero-spam baseline caching. Made with AI.

📅 AI-powered academic deadline assistant that uses Gemini Vision to extract assignments, exams, projects & submission dates from academic documents, with smart deadline Q&A and Telegram notifications. 🤖📸💬📲

Full-circle image roll estimation with calibrated abstention. Open weights, Apache-2.0. By ORTUS AI, the team behind CHEQIT.

JSON 剪辑单驱动的本地 FFmpeg 流水线：计划校验、字幕与配音、成片解码检查和局部修补保真度记录。