Papers › Wavelet-based Unsupervised Label-to-Image Translation
Wavelet-based Unsupervised Label-to-Image Translation
George Eskandar, Mohamed Abdelsamad, Karim Armanious, Shuai Zhang, Bin Yang
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a semantic layout is used to generate a photorealistic image. State-of-the-art conditional Generative Adversarial Networks (GANs) need a huge amount of paired data to accomplish this task while generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and learn correspondences in appearance instead of semantic content. Starting from the assumption that a high quality generated image should be segmented back to its semantic layout, we propose a new Unsupervised paradigm for SIS (USIS) that makes use of a self-supervised segmentation loss and whole image wavelet based discrimination. Furthermore, in order to match the high-frequency distribution of real images, a novel generator architecture in the wavelet domain is proposed. We test our methodology on 3 challenging datasets and demonstrate its ability to bridge the performance gap between paired and unpaired models.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image-to-Image Translation | ADE20K Labels-to-Photos | USIS-Wavelet | FID | 34.5 | #12 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | ADE20K Labels-to-Photos | USIS-Wavelet | mIoU | 16.95 | #12 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | COCO-Stuff Labels-to-Photos | USIS-Wavelet | FID | 28.6 | #12 of 15 | Archive leaderboard | report |
| Image-to-Image Translation | COCO-Stuff Labels-to-Photos | USIS-Wavelet | mIoU | 13.4 | #12 of 15 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | USIS-Wavelet | FID | 50.14 | #14 of 21 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | USIS-Wavelet | mIoU | 42.32 | #14 of 21 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections