taesungp/contrastive-unpaired-translation
A PyTorch implementation of Contrastive Unpaired Translation (CUT) for unpaired image-to-image domain translation.
Not currently ranked — collecting fresh signals.
star history
This repository provides a PyTorch implementation of unpaired image-to-image translation using patchwise contrastive learning combined with adversarial learning. The method avoids hand-crafted losses and inverse networks that CycleGAN uses, resulting in faster and more memory-efficient training. The approach can be extended to single-image training where each domain consists of only one image. Published at ECCV 2020.
Frequently asked
- What is taesungp/contrastive-unpaired-translation?
- A PyTorch implementation of Contrastive Unpaired Translation (CUT) for unpaired image-to-image domain translation.
- Is contrastive-unpaired-translation open source?
- Yes — taesungp/contrastive-unpaired-translation is an open-source project tracked on heatdrop.
- What language is contrastive-unpaired-translation written in?
- taesungp/contrastive-unpaired-translation is primarily written in Python.
- How popular is contrastive-unpaired-translation?
- taesungp/contrastive-unpaired-translation has 2.5k stars on GitHub.
- Where can I find contrastive-unpaired-translation?
- taesungp/contrastive-unpaired-translation is on GitHub at https://github.com/taesungp/contrastive-unpaired-translation.