Papers › USIS: Unsupervised Semantic Image Synthesis
USIS: Unsupervised Semantic Image Synthesis
George Eskandar, Mohamed Abdelsamad, Karim Armanious, Bin Yang
Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend on a huge amount of labeled data and cannot be applied in an unpaired setting. On the other hand, generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and feed them to traditional convolutional networks, which then learn correspondences in appearance instead of semantic content. In this initial work, we propose a new Unsupervised paradigm for Semantic Image Synthesis (USIS) as a first step towards closing the performance gap between paired and unpaired settings. Notably, the framework deploys a SPADE generator that learns to output images with visually separable semantic classes using a self-supervised segmentation loss. Furthermore, in order to match the color and texture distribution of real images without losing high-frequency information, we propose to use whole image wavelet-based discrimination. We test our methodology on 3 challenging datasets and demonstrate its ability to generate multimodal photorealistic images with an improved quality in the unpaired setting.
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 | FID | 33.2 | #11 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | ADE20K Labels-to-Photos | USIS | mIoU | 17.38 | #11 of 16 | Archive leaderboard | report |
| Image-to-Image Translation | COCO-Stuff Labels-to-Photos | USIS | FID | 27.8 | #11 of 15 | Archive leaderboard | report |
| Image-to-Image Translation | COCO-Stuff Labels-to-Photos | USIS | mIoU | 14.06 | #11 of 15 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | USIS | FID | 53.67 | #13 of 21 | Archive leaderboard | report |
| Image-to-Image Translation | Cityscapes Labels-to-Photo | USIS | mIoU | 44.78 | #13 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