Metraipolis › archive › dc_bef7d352d0d6

Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement — arXiv:2611.03390

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03390
License (as archived)
CC0-1.0
Archived
2026-11-03T18:41:29.960Z
SHA-256 of the archived text
e8dce4d76f6183d064c89e99702be7b37b82eb28b4e034f87a646f85e2c9fdcc
Stable URL of this page
https://metraipolis.com/documento/dc_bef7d352d0d6

How to cite

Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement — arXiv:2611.03390 — arXiv (en), https://arxiv.org/abs/2611.03390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bef7d352d0d6 (Metraipolis archive dc_bef7d352d0d6, sha256 e8dce4d76f6183d064c89e99702be7b37b82eb28b4e034f87a646f85e2c9fdcc)
BibTeX
@misc{dcbef7d352d0d6,
  title = {Progressive Multi-Scale Super-Resolution via Cascaded Bicubic Anchors and Inter-Scale Mutual Refinement — arXiv:2611.03390},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03390},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bef7d352d0d6; sha256 e8dce4d76f6183d064c89e99702be7b37b82eb28b4e034f87a646f85e2c9fdcc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Super-resolution networks are trained for one magnification factor, so several output resolutions require several models. We propose PMS-SR, a progressive single-input multiple-output network that produces x2, x4, and x8 results in one forward pass, with a Transformer backbone on the low-resolution grid. In Stage 1, each scale is predicted as a residual over the detached bicubic upsampling of the previous scale's prediction. With Dirac and zero initialization, training starts exactly from the bicubic cascade, and each head adds only the band the previous scale lacks. In Stage 2, inter-scale mutual refinement couples the scales in both directions through space-to-depth feedback, deformable alignment, and per-pixel fusion, so x8 features refine the x2 output. Trained on DF2K, the 7.95M-parameter model achieves a higher PSNR than every compared multi-scale method at x4 and x8 on all five standard benchmarks. At x8, it outperforms the x8-specific DRN-L on all of them, leads all compared methods on Urban100, and is within 0.13 dB of the best result elsewhere. Against three single-scale SwinIR-M models, PMS-SR uses 22% of the parameters, runs 2.9x faster on BSD100 inputs, and its outputs agree 6.7-12.4 dB more closely. Code and pretrained models will be released at this https URL upon acceptance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2611.03390 — 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 2026-11-03T18:12:54.806Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).