Metraipolis › archive › dc_fc3a80bb2801

SketchSense: Learning to Interpret Imperfect Sketch Guidance for Image Inpainting — arXiv:2608.13186

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.13186
License (as archived): CC0-1.0
Archived: 2026-10-19T04:55:50.169Z
SHA-256 of the archived text: 0de9a3accae46201d6e1d0dd0ea63e73359efce2e746f434292efe09cab45b5f
Stable URL of this page: https://metraipolis.com/documento/dc_fc3a80bb2801

How to cite

SketchSense: Learning to Interpret Imperfect Sketch Guidance for Image Inpainting — arXiv:2608.13186 — arXiv (en), https://arxiv.org/abs/2608.13186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc3a80bb2801 (Metraipolis archive dc_fc3a80bb2801, sha256 0de9a3accae46201d6e1d0dd0ea63e73359efce2e746f434292efe09cab45b5f)

BibTeX

@misc{dcfc3a80bb2801,
  title = {SketchSense: Learning to Interpret Imperfect Sketch Guidance for Image Inpainting — arXiv:2608.13186},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13186},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc3a80bb2801; sha256 0de9a3accae46201d6e1d0dd0ea63e73359efce2e746f434292efe09cab45b5f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sketch-guided image inpainting provides intuitive structural control, yet real sketches often mix reliable global intent with locally crowded, displaced, incomplete, or deliberately unconventional strokes. Existing approaches typically either retain the input sketch as a fixed condition throughout denoising or refine it into a clean structure before RGB synthesis. The former assumes uniformly reliable strokes and can propagate local errors throughout generation; the latter must resolve ambiguous structure before emerging appearance and semantic context become available. We propose SketchSense, a framework that interprets imperfect sketch guidance by synchronously denoising interacting RGB and structure streams. Bidirectional Attention Fusion couples appearance generation with structural recovery, producing a refined structure that exposes the model's evolving sketch interpretation. A phrase-level objective aligns the semantic grounding of the two streams. Sketch-Aware Spatial Regulation further adapts sketch use to local generation states by modulating attention and the fusion process, while an optional signed prior injects preserve-versus-correct intent into feature representations and attention behavior. Experiments on natural and structurally complex imagery show substantial gains over existing methods in both restoration quality and structural fidelity.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.13186 — 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 2026-10-19T04:46:30.162Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).