Open Source Computer Vision Projects
Discover 67 open source Computer Vision repositories from GitHub, each with an analysis of what it does, key features, use cases and alternatives. Computer Vision projects here are most often combined with Python, Machine Learning and Deep Learning. Last updated October 3, 2026.
67 repositories · updated October 3, 2026
LivePortrait: Animate Portraits from Images and Video
LivePortrait is a PyTorch project for animating human and animal portraits using a driving video or motion template. It supports portrait video editing and offers command-line inference and a Gradio interface.
Ollama-OCR: Extract Text from Images and PDFs with Vision Models
Ollama-OCR uses vision-language models served by Ollama to extract text and structured content from images and PDFs. It offers a Python package for single or batch processing and a Streamlit interface for interactive use.
Leffa: Generate Controllable Person Images
Leffa is a diffusion-based framework for virtual try-on and pose transfer that aims to preserve fine-grained details from reference images. It is suited to researchers and developers building or evaluating controllable person-image generation systems.
smolvlm-realtime-webcam: Analyze Webcam Video with SmolVLM
A browser-based demo sends webcam frames to a llama.cpp server running SmolVLM 500M for real-time visual analysis. It suits developers exploring local vision models and webcam workflows, with performance depending on the model server and hardware.
DeepFaceLive: Real-Time Face Swapping for Video
DeepFaceLive is a Windows desktop app for swapping faces from a webcam or video in real time, and for animating a still face image. It targets streamers and video-call users with a compatible GPU.
jscanify: Detect and Straighten Paper in Images
jscanify is a JavaScript document-scanning library for detecting paper in images and correcting perspective. It uses OpenCV.js and supports browser and Node.js workflows, including live camera input.
face-cropper: Crop and Align Faces in Images
A Python tool that detects faces and crops them using MediaPipe FaceDetection and FaceMesh. It can optionally remove background pixels and correct face roll, making it useful for image preprocessing and lightweight real-time applications.