#193 · Primary category: Computer Vision
DDColor
[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders
Project last updated:01/17/26
GitHub Stars
1.5K
Forks
169
Contributors
6
License
Apache-2.0
Why we included this project
DDColor does one thing well: it puts believable color back into black-and-white photos. It's an ICCV 2023 method from Alibaba's DAMO Academy, and the code here lets you run it yourself with just PyTorch. The model learns reusable color tokens from multi-scale visual features, which tends to look more natural than earlier deep colorizers. Pretrained weights ship with the repo, including a lighter 'tiny' variant, and there are Replicate and ModelScope demos if you want to sample the output before installing anything. People restoring old family photos, digitized film archives, or even anime game landscapes that want a more realistic finish will find a solid baseline they can retrain on their own data.
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)