Metraipolis › archive › dc_af644f03e41f

Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients — arXiv:2609.38591

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.38591
License (as archived): CC0-1.0
Archived: 2026-10-07T14:45:22.829Z
SHA-256 of the archived text: 7214901b407e8f35a889ddc373441e950b912eba028e923636ca1c8bfb708376
Stable URL of this page: https://metraipolis.com/documento/dc_af644f03e41f

How to cite

Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients — arXiv:2609.38591 — arXiv (en), https://arxiv.org/abs/2609.38591 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_af644f03e41f (Metraipolis archive dc_af644f03e41f, sha256 7214901b407e8f35a889ddc373441e950b912eba028e923636ca1c8bfb708376)

BibTeX

@misc{dcaf644f03e41f,
  title = {Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients — arXiv:2609.38591},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38591},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_af644f03e41f; sha256 7214901b407e8f35a889ddc373441e950b912eba028e923636ca1c8bfb708376},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38591. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this work, we propose Restoring without Forgetting (RwF), a filter-level continual adaptation framework for image restoration built upon a critical observation: task-specific knowledge is centered in a small subset of filters and can be separated from those reconstructing general content. RwF first performs parameter-space integrated gradients attribution to localize degradation-critical filters in a coarse-to-fine manner. It then adapts to new tasks by generating task-specific filters from a filter bank using compact factorized low-rank transformations, further augmented with cross-task attention and prototypical contrastive learning, and lastly assembles them back only at localized positions. Experiments on six restoration tasks show that RwF effectively avoids forgetting and achieves competitive restoration quality against all-in-one methods that have full data access, and outperforms LoRA-style adaptation with $\sim$10$\times$ fewer additional parameters. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.38591 — 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 2026-10-07T14:19:00.579Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).