Metraipolis › archive › dc_de9cf2fbd75f

Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models — arXiv:2608.30305

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30305
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:26.227Z
SHA-256 of the archived text
e5d1a32af0ec5e2c51d05745e0ca705007749885c3a05e2f454ad51eb8cb9d71
Stable URL of this page
https://metraipolis.com/documento/dc_de9cf2fbd75f

How to cite

Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models — arXiv:2608.30305 — arXiv (en), https://arxiv.org/abs/2608.30305 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de9cf2fbd75f (Metraipolis archive dc_de9cf2fbd75f, sha256 e5d1a32af0ec5e2c51d05745e0ca705007749885c3a05e2f454ad51eb8cb9d71)
BibTeX
@misc{dcde9cf2fbd75f,
  title = {Learning to Restore More: Continual Capability Expansion for Pretrained Image Restoration Models — arXiv:2608.30305},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30305},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de9cf2fbd75f; sha256 e5d1a32af0ec5e2c51d05745e0ca705007749885c3a05e2f454ad51eb8cb9d71},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30305. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image restoration models are typically trained with a fixed set of capabilities. When new restoration requirements emerge, existing solutions usually train additional models or jointly retrain the original model with both new and historical data. Instead of designing another restoration backbone, we investigate how a trained restorer can continually acquire new capabilities without forgetting those learned previously. We propose RestoreMore, a continual capability-expansion framework that preserves the pretrained restoration model as a frozen capability anchor and learns residual expansion modules for newly arriving degradations. RestoreMore introduces a capability-oriented bi-level routing mechanism at multiple feature stages. The first routing level identifies restoration capabilities relevant to the current input, while the second selects and combines a sparse set of complementary degradation experts. This design enables newly introduced tasks to selectively reuse historical restoration knowledge and progressively enriches the expert bank available for subsequent restoration tasks. Extensive experiments on a wide range of restoration benchmarks demonstrate that RestoreMore consistently acquires new restoration abilities while preserving and improving previously learned capabilities.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.30305 — 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 2026-10-17T09:28:48.131Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).