Computer Vision

"World Models in a Closed-Loop World" (ICLR'26 Oral)

PolyLayout: Multi-room Manhattan Layout Estimation (ECCV 2026)

Open-source, under-$35 AI navigation glasses for blind & low-vision people — safety-first guidance, printable enclosure, community build kit.

Open-source AI paper index and fine-grained topic atlas across major conferences and journals.

QQ经典农场机器人（AI视觉版本）

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

Real-time parking lot occupancy detection using existing security cameras and on-device computer vision.

The open platform for AI on your cameras: a self-hosted NVR (ONVIF/RTSP, recording, WebRTC) running any AI model through one open contract, with an app SDK and one-click apps. New capabilities arrive as software, not new boxes. Air-gapped or connected, audited end to end. Home Assistant built in. AGPLv3. A Frigate/ZoneMinder alternative.

OculiX — Visual Automation IDE. If you can see it, you can automate it.

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.

PhenoPixel: A web-based bioimage analysis platform for bacterial single-cell microscopy analytics.

Model-agnostic state layer for world models — turn any detector (YOLO · VLM · DINO) into one standard, queryable stream of events + latent state. numpy-only, runs on CPU at the edge.

Unbagrnd - Free, Fast & Open-source AI-powered background remover for Windows, macOS, Linux and Android.

Lightweight self-hosted NVR in Go — single static binary, zero dependencies, embedded web UI. RTSP/ONVIF/Xiaomi/GB28181/WHIP cameras, RTMP/SRT push-in, WebRTC/HLS/FLV live view, audio, timelapse, continuous playback, S3 offload, browser-side AI detection. Runs on low-power ARM.

运动世界校园纯 Python 协议实现，包含 NetSecKit 4.2.4、GeeTest v4、全链路协议分析与自动化套件，脱离 Android App 与 Native SO 依赖。

Background removal that keeps what matters: glass, camouflage, text, glow and line art. BiRefNet fine-tune, MIT.

Sleek, mobile-friendly web UI for NVIDIA LocateAnything-3B — open-vocabulary object detection & grounding on your own GPU, via one docker compose up.

a library for background removal models

Open-source video processing core and CLI. Search and annotate local videos with your own model endpoints.

Convert 2D videos and photos into interactive 3D scenes using Gaussian splatting backends (VGGT, LongSplat, DepthSplat, SHARP, TripoSplat), Rerun, and the SuperSplat editor.

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

Code for paper "VkSplat: High-Performance 3DGS Training in Vulkan Compute"

[AAAI 2026] The Official Implementation for "Anomagic: Crossmodal Prompt-driven Zero-shot Anomaly Generation"

Official Code for ECCV 2026 paper "EgoExoMoCap: Distributed Ego-Exo Human Motion Capture"

SfM, MVS, visual-inertial SLAM, 3D Gaussian Splatting and map-based localization in Rust

基于 Windows Credential Provider 框架的摄像头人脸识别解锁工具。让不支持Windows Hello的的电脑也能够体验“人脸登录”。

[CVPR 2026] Thinking in 360°: Humanoid Visual Search in the Wild

We have summarised all 3D anomaly detection methods and datasets (still updating). 多模态，点云和姿势无关异常检测的综述仓库（持续更新）

Official implementation of paper LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

Eva01 is NOT an assistant. She is an AI being with her own mind, feelings, and intrinsic drives. Multimodal, Modular design. Built-in voice & face recognition. Plug'n play tools. Compatible with ChatGPT, Claude, Deepseek, Gemini, Grok, and Ollama. Explore the possibilities of Human-AI Interaction.

Camera-only closed-loop driving agent for Forza Horizon 6, with geometry as the control interface.

🤖 基于深度学习的AI量化投资系统 | Vision-Based Quantitative Trading System with Deep Learning

计算机毕业设计、机器学习毕业设计、深度学习毕业设计、原创AI项目【源码+论文】

A curated, learning-friendly list of egocentric (first-person) vision & embodied AI resources: papers, datasets, code, models, toolkits, challenges and tutorials, covering both classic foundational works and cutting-edge advances, catering to research initiation and industrial deployment.

GTR: Gated Token Recurrence for Efficient Dense Prediction

NEWTON: Agentic Planning for Physically Grounded Video Generation

🌟 [Survey] A curated collection of research papers, models, and resources tracing the evolution from specialized models to unified world models.

GPS-denied drone navigation layer: optical flow + offline map geo-match + EKF → MAVLink (sim-validated).

基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat

Privacy-first, local-only barcode scanning SDK for Web, Node.js, React, iOS and Android with multi-format decoding, realtime tracking, batch scanning, and native/WASM engines.

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

杀戮尖塔2 数字琥珀自动画板 | A Python automation drawing tool for Slay the Spire 2

Image Pipeline Playground

Local-first AI photo culling for professional photographers — 6-axis rubric, XMP/IPTC export, Lightroom & Capture One ready.

Fit compact primitive assemblies (SuperFrusta, cuboids, superquadrics) to 3D shapes via residual fitting. CVPR 2026.

Flatbed-scanner photometric stereo for generating normal, albedo, height, and alpha texture maps.

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.

nte neverness to everness download pc auto fish ray tracing bot teleport esp speedhack macro script nte fishingbot cheeto maaframework oknte maante game automation assistant dialogue skip daily rewards helper utility pc gaming trainer automatic assistant hotta studio open source github download

Official Implementation of NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering