An Optimal Transport Perspective on Unpaired Image Super-Resolution
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911042917892096 |
|---|---|
| author | Gazdieva, Milena Mokrov, Petr Rout, Litu Korotin, Alexander Kravchenko, Andrey Filippov, Alexander Burnaev, Evgeny |
| author_facet | Gazdieva, Milena Mokrov, Petr Rout, Litu Korotin, Alexander Kravchenko, Andrey Filippov, Alexander Burnaev, Evgeny |
| contents | Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques. As a result, the tasks are usually approached by unpaired techniques based on Generative Adversarial Networks (GANs), which yield complex training losses with several regularization terms, e.g., content or identity losses. While GANs usually provide good practical performance, they are used heuristically, i.e., theoretical understanding of their behaviour is yet rather limited. We theoretically investigate optimization problems which arise in such models and find two surprising observations. First, the learned SR map is always an optimal transport (OT) map. Second, we theoretically prove and empirically show that the learned map is biased, i.e., it does not actually transform the distribution of low-resolution images to high-resolution ones. Inspired by these findings, we investigate recent advances in neural OT field to resolve the bias issue. We establish an intriguing connection between regularized GANs and neural OT approaches. We show that unlike the existing GAN-based alternatives, these algorithms aim to learn an unbiased OT map. We empirically demonstrate our findings via a series of synthetic and real-world unpaired SR experiments. Our source code is publicly available at https://github.com/milenagazdieva/OT-Super-Resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_01116 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | An Optimal Transport Perspective on Unpaired Image Super-Resolution Gazdieva, Milena Mokrov, Petr Rout, Litu Korotin, Alexander Kravchenko, Andrey Filippov, Alexander Burnaev, Evgeny Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Real-world image super-resolution (SR) tasks often do not have paired datasets, which limits the application of supervised techniques. As a result, the tasks are usually approached by unpaired techniques based on Generative Adversarial Networks (GANs), which yield complex training losses with several regularization terms, e.g., content or identity losses. While GANs usually provide good practical performance, they are used heuristically, i.e., theoretical understanding of their behaviour is yet rather limited. We theoretically investigate optimization problems which arise in such models and find two surprising observations. First, the learned SR map is always an optimal transport (OT) map. Second, we theoretically prove and empirically show that the learned map is biased, i.e., it does not actually transform the distribution of low-resolution images to high-resolution ones. Inspired by these findings, we investigate recent advances in neural OT field to resolve the bias issue. We establish an intriguing connection between regularized GANs and neural OT approaches. We show that unlike the existing GAN-based alternatives, these algorithms aim to learn an unbiased OT map. We empirically demonstrate our findings via a series of synthetic and real-world unpaired SR experiments. Our source code is publicly available at https://github.com/milenagazdieva/OT-Super-Resolution. |
| title | An Optimal Transport Perspective on Unpaired Image Super-Resolution |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2202.01116 |