zhangmozhe/Deep-Exemplar-based-Video-Colorization

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".

49
/ 100
Emerging

Leverages exemplar-based reference images to guide temporal color propagation across video frames, using a PyTorch architecture with VGG19 perceptual loss for training. Supports both automatic reference retrieval from ImageNet and manual exemplar selection, with inference scaling to handle arbitrary resolutions while maintaining the 1:2 aspect ratio used during training. Includes full training pipeline with synthetic video augmentation from ImageNet, enabling customization beyond the provided pretrained model.

370 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

370

Forks

88

Language

Python

License

MIT

Last pushed

Oct 29, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zhangmozhe/Deep-Exemplar-based-Video-Colorization"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.