Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915602881314816 |
|---|---|
| author | Becker, Alexander Daudt, Rodrigo Caye Narnhofer, Dominik Peters, Torben Metzger, Nando Wegner, Jan Dirk Schindler, Konrad |
| author_facet | Becker, Alexander Daudt, Rodrigo Caye Narnhofer, Dominik Peters, Torben Metzger, Nando Wegner, Jan Dirk Schindler, Konrad |
| contents | Recent approaches to arbitrary-scale single image super-resolution (ASR) use neural fields to represent continuous signals that can be sampled at arbitrary resolutions. However, point-wise queries of neural fields do not naturally match the point spread function (PSF) of pixels, which may cause aliasing in the super-resolved image. Existing methods attempt to mitigate this by approximating an integral version of the field at each scaling factor, compromising both fidelity and generalization. In this work, we introduce neural heat fields, a novel neural field formulation that inherently models a physically exact PSF. Our formulation enables analytically correct anti-aliasing at any desired output resolution, and -- unlike supersampling -- at no additional cost. Building on this foundation, we propose Thera, an end-to-end ASR method that substantially outperforms existing approaches, while being more parameter-efficient and offering strong theoretical guarantees. The project page is at https://therasr.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_17643 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields Becker, Alexander Daudt, Rodrigo Caye Narnhofer, Dominik Peters, Torben Metzger, Nando Wegner, Jan Dirk Schindler, Konrad Computer Vision and Pattern Recognition Recent approaches to arbitrary-scale single image super-resolution (ASR) use neural fields to represent continuous signals that can be sampled at arbitrary resolutions. However, point-wise queries of neural fields do not naturally match the point spread function (PSF) of pixels, which may cause aliasing in the super-resolved image. Existing methods attempt to mitigate this by approximating an integral version of the field at each scaling factor, compromising both fidelity and generalization. In this work, we introduce neural heat fields, a novel neural field formulation that inherently models a physically exact PSF. Our formulation enables analytically correct anti-aliasing at any desired output resolution, and -- unlike supersampling -- at no additional cost. Building on this foundation, we propose Thera, an end-to-end ASR method that substantially outperforms existing approaches, while being more parameter-efficient and offering strong theoretical guarantees. The project page is at https://therasr.github.io. |
| title | Thera: Aliasing-Free Arbitrary-Scale Super-Resolution with Neural Heat Fields |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.17643 |