Metraipolis › archive › dc_09b14f477c97

Efficient and Faithful High-Resolution Image Editing with Sparse Cross-Resolution Denoising — arXiv:2611.04416

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04416
License (as archived)
CC0-1.0
Archived
2026-11-04T12:56:24.344Z
SHA-256 of the archived text
ee4890edc45b7da4053a75976d3bb656d04475b75e183cd47d7b6383b37f072e
Stable URL of this page
https://metraipolis.com/documento/dc_09b14f477c97

How to cite

Efficient and Faithful High-Resolution Image Editing with Sparse Cross-Resolution Denoising — arXiv:2611.04416 — arXiv (en), https://arxiv.org/abs/2611.04416 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09b14f477c97 (Metraipolis archive dc_09b14f477c97, sha256 ee4890edc45b7da4053a75976d3bb656d04475b75e183cd47d7b6383b37f072e)
BibTeX
@misc{dc09b14f477c97,
  title = {Efficient and Faithful High-Resolution Image Editing with Sparse Cross-Resolution Denoising — arXiv:2611.04416},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04416},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09b14f477c97; sha256 ee4890edc45b7da4053a75976d3bb656d04475b75e183cd47d7b6383b37f072e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04416. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Instruction-based image editors still primarily operate at 1K, whereas practical editing increasingly requires faithful 2K/4K outputs. Dense high-resolution adaptation preserves the editing trajectory but incurs expensive target-source attention; editing at 1K followed by external refinement is cheaper but can separate detail restoration from the editing trajectory. We introduce FLASH, a native high-resolution editor based on sparse cross-resolution denoising. A frozen 1K branch provides a semantic and structural anchor, while a target-resolution branch reconstructs local detail within the same Transformer. An asymmetric topology retains full 1K attention, guides high-resolution queries with spatially aligned low-resolution noisy-target states, and confines high-resolution target-reference interaction to local Halo neighborhoods. Resolution-specific diffusion-state mapping and spatial YaRN adapt the pretrained editor to larger grids. An optional, training-free progressive path replaces early high-resolution denoising with a 1K prefix and completes refinement in the same editor. On VINS-4KEval, the direct model achieves the strongest structural fidelity among the compared methods at both 2K and 4K. A separate 4K forward benchmark with R = 1 records 4.2x faster total forward execution and 25.3x faster attention than dense target-reference attention. Progressive inference reduces end-to-end 4K latency by 30.5%, with a modest quality cost.

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/2611.04416 — 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 2026-11-04T12:33:47.143Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).