#335 · Primary category: Computer Vision
interactive-deep-colorization
Deep learning software for colorizing black and white images with a few clicks.
Project last updated:07/29/22
GitHub Stars
2.7K
Forks
446
Contributors
9
License
MIT
Why we included this project
Photographers and archivists working through large collections of old or monochrome photos have a concrete use for this. The colorizer is interactive rather than fully automatic: you drop a few colored strokes or click hints, and a learned deep prior from the authors' SIGGRAPH 2017 paper fills the rest of the frame with consistent color, which is what you want when accuracy or historical plausibility matters. The repo bundles a reference model, a barebones Jupyter notebook for quick experiments, and the full Qt-based GUI from the paper, where hint points can be repositioned and recolored as you work. It runs on Caffe or PyTorch and handles CPU or GPU, so you can test the workflow cheaply before committing to a production setup. The approach also shipped as a colorize feature in Adobe Photoshop Elements 2020, a decent sign that the interaction model holds up outside the lab.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)