Guiding WaveMamba with Frequency Maps for Image Debanding
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912755310657536 |
|---|---|
| author | Wang, Xinyi Tasmoc, Smaranda Anantrasirichai, Nantheera Katsenou, Angeliki |
| author_facet | Wang, Xinyi Tasmoc, Smaranda Anantrasirichai, Nantheera Katsenou, Angeliki |
| contents | Compression at low bitrates in modern codecs often introduces banding artifacts, especially in smooth regions such as skies. These artifacts degrade visual quality and are common in user-generated content due to repeated transcoding. We propose a banding restoration method that employs the Wavelet State Space Model and a frequency masking map to preserve high-frequency details. Furthermore, we provide a benchmark of open-source banding restoration methods and evaluate their performance on two public banding image datasets. Experimentation on the available datasets suggests that the proposed post-processing approach effectively suppresses banding compared to the state-of-the-art method (a DBI value of 0.082 on BAND-2k) while preserving image textures. Visual inspections of the results confirm this. Code and supplementary material are available at: https://github.com/xinyiW915/Debanding-PCS2025. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11331 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Guiding WaveMamba with Frequency Maps for Image Debanding Wang, Xinyi Tasmoc, Smaranda Anantrasirichai, Nantheera Katsenou, Angeliki Image and Video Processing Computer Vision and Pattern Recognition Compression at low bitrates in modern codecs often introduces banding artifacts, especially in smooth regions such as skies. These artifacts degrade visual quality and are common in user-generated content due to repeated transcoding. We propose a banding restoration method that employs the Wavelet State Space Model and a frequency masking map to preserve high-frequency details. Furthermore, we provide a benchmark of open-source banding restoration methods and evaluate their performance on two public banding image datasets. Experimentation on the available datasets suggests that the proposed post-processing approach effectively suppresses banding compared to the state-of-the-art method (a DBI value of 0.082 on BAND-2k) while preserving image textures. Visual inspections of the results confirm this. Code and supplementary material are available at: https://github.com/xinyiW915/Debanding-PCS2025. |
| title | Guiding WaveMamba with Frequency Maps for Image Debanding |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.11331 |