Metraipolis › archive › dc_d1ce5b243f23

MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration — arXiv:2608.14543

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.14543
License (as archived)
CC0-1.0
Archived
2026-10-19T04:04:32.728Z
SHA-256 of the archived text
eb83bc31a95399ba7b36e7caa2006da514859dc5ed268823c8cbf6ab34230221
Stable URL of this page
https://metraipolis.com/documento/dc_d1ce5b243f23

How to cite

MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration — arXiv:2608.14543 — arXiv (en), https://arxiv.org/abs/2608.14543 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d1ce5b243f23 (Metraipolis archive dc_d1ce5b243f23, sha256 eb83bc31a95399ba7b36e7caa2006da514859dc5ed268823c8cbf6ab34230221)
BibTeX
@misc{dcd1ce5b243f23,
  title = {MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration — arXiv:2608.14543},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.14543},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d1ce5b243f23; sha256 eb83bc31a95399ba7b36e7caa2006da514859dc5ed268823c8cbf6ab34230221},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14543. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-resolution image restoration from degraded inputs is challenging because it must preserve global structural consistency while recovering fine-grained local details, especially at 4K resolution where direct diffusion-based restoration is computationally expensive and prone to repeated or inconsistent textures. In this work, we introduce MagnifiQ, an image restoration framework that progressively upscales and restores images across resolutions, e.g., from 1024x1024 to 4096x4096. Our approach leverages a pre-trained text-to-image diffusion model such as SDXL and adapts it for more scalable high-resolution inference by replacing its original self-attention layers with convolutional operations whose computational cost grows linearly with image resolution. We further propose a progressive upscaling strategy that iteratively restores images over multiple resolution stages, refining each intermediate output rather than directly hallucinating the final 4K image, thereby improving global coherence and reducing high-resolution artifacts. To enhance local details while controlling content drift, MagnifiQ uses patch-specific text prompts that provide spatially localized semantic guidance during restoration. Extensive experiments on synthetic and real-world degraded images show that MagnifiQ outperforms prior diffusion-based restoration methods in perceptual quality and human preference, producing sharper textures and more coherent 4K results while offering practical speed--quality trade-offs through its scalable backbone and progressive design.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-17 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.14543 — 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 2026-10-19T03:57:57.963Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).