Toward task-driven satellite image super-resolution
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908275517161472 |
|---|---|
| author | Ziaja, Maciej Kowaleczko, Pawel Kostrzewa, Daniel Longépé, Nicolas Kawulok, Michal |
| author_facet | Ziaja, Maciej Kowaleczko, Pawel Kostrzewa, Daniel Longépé, Nicolas Kawulok, Michal |
| contents | Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining outstanding results, generating images of high perceptual quality. However, it often remains unclear whether the reconstructed details are close to the actual ground-truth information and whether they constitute a more valuable source for image analysis algorithms. In the reported work, we address the latter problem, and we present our efforts toward learning super-resolution algorithms in a task-driven way to make them suitable for generating high-resolution images that can be exploited for automated image analysis. In the reported initial research, we propose a methodological approach for assessing the existing models that perform computer vision tasks in terms of whether they can be used for evaluating super-resolution reconstruction algorithms, as well as training them in a task-driven way. We support our analysis with experimental study and we expect it to establish a solid foundation for selecting appropriate computer vision tasks that will advance the capabilities of real-world super-resolution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15474 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Toward task-driven satellite image super-resolution Ziaja, Maciej Kowaleczko, Pawel Kostrzewa, Daniel Longépé, Nicolas Kawulok, Michal Computer Vision and Pattern Recognition Super-resolution is aimed at reconstructing high-resolution images from low-resolution observations. State-of-the-art approaches underpinned with deep learning allow for obtaining outstanding results, generating images of high perceptual quality. However, it often remains unclear whether the reconstructed details are close to the actual ground-truth information and whether they constitute a more valuable source for image analysis algorithms. In the reported work, we address the latter problem, and we present our efforts toward learning super-resolution algorithms in a task-driven way to make them suitable for generating high-resolution images that can be exploited for automated image analysis. In the reported initial research, we propose a methodological approach for assessing the existing models that perform computer vision tasks in terms of whether they can be used for evaluating super-resolution reconstruction algorithms, as well as training them in a task-driven way. We support our analysis with experimental study and we expect it to establish a solid foundation for selecting appropriate computer vision tasks that will advance the capabilities of real-world super-resolution. |
| title | Toward task-driven satellite image super-resolution |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15474 |