Parameter-free structure-texture image decomposition by unrolling
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917959180484608 |
|---|---|
| author | Girometti, Laura Aujol, Jean-François Guennec, Antoine Traonmilin, Yann |
| author_facet | Girometti, Laura Aujol, Jean-François Guennec, Antoine Traonmilin, Yann |
| contents | In this work, we propose a parameter-free and efficient method to tackle the structure-texture image decomposition problem. In particular, we present a neural network LPR-NET based on the unrolling of the Low Patch Rank model. On the one hand, this allows us to automatically learn parameters from data, and on the other hand to be computationally faster while obtaining qualitatively similar results compared to traditional iterative model-based methods. Moreover, despite being trained on synthetic images, numerical experiments show the ability of our network to generalize well when applied to natural images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13354 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parameter-free structure-texture image decomposition by unrolling Girometti, Laura Aujol, Jean-François Guennec, Antoine Traonmilin, Yann Computer Vision and Pattern Recognition Numerical Analysis Image and Video Processing 68U10, 90C26 In this work, we propose a parameter-free and efficient method to tackle the structure-texture image decomposition problem. In particular, we present a neural network LPR-NET based on the unrolling of the Low Patch Rank model. On the one hand, this allows us to automatically learn parameters from data, and on the other hand to be computationally faster while obtaining qualitatively similar results compared to traditional iterative model-based methods. Moreover, despite being trained on synthetic images, numerical experiments show the ability of our network to generalize well when applied to natural images. |
| title | Parameter-free structure-texture image decomposition by unrolling |
| topic | Computer Vision and Pattern Recognition Numerical Analysis Image and Video Processing 68U10, 90C26 |
| url | https://arxiv.org/abs/2503.13354 |