Metraipolis › archive › dc_b5bca43cb14b

SASFormer: Stage-Aware Selective Attention Transformer for All-in-One Blind Image Restoration — arXiv:2611.00523

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00523
License (as archived)
CC0-1.0
Archived
2026-11-03T18:53:10.171Z
SHA-256 of the archived text
2a94ea1cf7e7fec78f6d1a091d47e13f158036bf19d1538beea30035c292e12d
Stable URL of this page
https://metraipolis.com/documento/dc_b5bca43cb14b

How to cite

SASFormer: Stage-Aware Selective Attention Transformer for All-in-One Blind Image Restoration — arXiv:2611.00523 — arXiv (en), https://arxiv.org/abs/2611.00523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5bca43cb14b (Metraipolis archive dc_b5bca43cb14b, sha256 2a94ea1cf7e7fec78f6d1a091d47e13f158036bf19d1538beea30035c292e12d)
BibTeX
@misc{dcb5bca43cb14b,
  title = {SASFormer: Stage-Aware Selective Attention Transformer for All-in-One Blind Image Restoration — arXiv:2611.00523},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00523},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5bca43cb14b; sha256 2a94ea1cf7e7fec78f6d1a091d47e13f158036bf19d1538beea30035c292e12d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

All-in-one image restoration aims to recover high-quality images from multiple degradation types using a single unified model. Recent methods improve unified restoration with hybrid attention, prompt learning, or routing mechanisms, but generally focus on enhancing degradation adaptivity while employing similar feature modeling strategies across network stages. Consequently, the distinct representation requirements of encoding and decoding under diverse degradations remain insufficiently explored. In this paper, we propose SASFormer, a Stage-Aware Selective Attention Transformer for all-in-one blind image restoration. SASFormer follows a stage-aware design principle: the encoder uses established hybrid channel-spatial attention to build robust content-preserving and degradation-aware representations, while the decoder employs adaptive selective attention for restoration-oriented reconstruction. To address the stage-specific requirements of decoder reconstruction, we develop Adaptive Selective Channel Self-Attention (ASCSA) and Adaptive Selective Spatial Self-Attention (ASSSA), enabling the decoder to dynamically identify restoration-relevant channel responses and spatial contexts. Specifically, ASCSA performs adaptive query-channel selection and attention masking, while ASSSA adaptively integrates spatial attention across multiple window sizes. Compact implicit prompts further modulate the selection process without requiring explicit degradation labels. Extensive experiments on 3-, 5-, and 11-degradation settings demonstrate that SASFormer achieves strong restoration performance with favorable parameter efficiency. Moreover, stage-wise representation analysis and ablation studies provide empirical support for the proposed stage-aware design and the effectiveness of decoder-side adaptive selection.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00523 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:16:52.884Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).