Computer Vision

Because commodity WiFi already bounces off your body, RuView uses cheap ESP32 nodes to detect presence, vital signs, and even body pose without cameras or wearables.

OmniParser turns raw screenshots into structured, labeled UI elements so vision-language models can finally click what they mean to click.

CMU's real-time multi-person pose estimator detects body, face, hands, and feet simultaneously—body runtime stays flat even as the crowd grows.

It exists to let developers run customized vision, text, and audio machine learning across mobile, web, and edge hardware without cloud round-trips.

An OCR model that asks how few vision tokens an LLM needs before it can no longer read the page.

It renders high-quality novel views of real-world scenes at 30 fps by replacing costly neural radiance fields with optimized 3D Gaussians.

Ultralytics wants to stop you from stitching together separate repos for every computer vision task by bundling detection, segmentation, tracking, and pose estimation into one YOLO-backed package.

YOLOv5 made real-time object detection as easy as `torch.hub.load`, then exported to everything from iOS to edge chips.

To give developers a zero-shot image segmentation model that generates masks from a click or a bounding box, no retraining required.

Google Research releases all its code and datasets in one place, which has grown so large that the README treats a full clone as a hazard.

It turns face swaps and lip-syncs into queued, retryable batch jobs instead of one-off scripts.

It bundles detection, recognition, alignment, and reconstruction into a single research-grade toolbox.

OpenCV is an open-source C++ computer vision library whose own README acts as a portal rather than a product page.

It rounds up hundreds of AI project links so you don't have to hunt them down yourself.

It turns images and PDFs into structured JSON and Markdown so your RAG pipeline doesn't have to squint.

Real-ESRGAN turns the ESRGAN research model into a practical tool for upscaling and restoring real-world images and videos using only synthetic training data.

Frigate performs real-time, local object detection on IP camera streams using OpenCV and TensorFlow, designed to integrate tightly with Home Assistant.

OCRmyPDF exists because most free OCR tools botch text placement, bloat file sizes, or mangle image resolution when trying to make scanned documents searchable.

It exists to handle the tedious wiring—annotations, dataset formats, tracking—that sits between a trained model and a useful application.

It glues together CRAFT detection and CRNN recognition so you can pull text out of images without tuning neural networks yourself.