Metraipolis › archive › dc_0abab8cc27fc

ScribbleEdit: A Benchmark for Scribble-Only Image Editing — arXiv:2610.09382

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09382
License (as archived)
CC0-1.0
Archived
2026-10-08T12:48:40.792Z
SHA-256 of the archived text
2ff00fe82bb3e112d2672d449af5e817d3dff73670e888083a52ed411ccb9e04
Stable URL of this page
https://metraipolis.com/documento/dc_0abab8cc27fc

How to cite

ScribbleEdit: A Benchmark for Scribble-Only Image Editing — arXiv:2610.09382 — arXiv (en), https://arxiv.org/abs/2610.09382 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0abab8cc27fc (Metraipolis archive dc_0abab8cc27fc, sha256 2ff00fe82bb3e112d2672d449af5e817d3dff73670e888083a52ed411ccb9e04)
BibTeX
@misc{dc0abab8cc27fc,
  title = {ScribbleEdit: A Benchmark for Scribble-Only Image Editing — arXiv:2610.09382},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09382},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0abab8cc27fc; sha256 2ff00fe82bb3e112d2672d449af5e817d3dff73670e888083a52ed411ccb9e04},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09382. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scribble-based interaction provides a lightweight and intuitive way for users to specify image editing intents in interactive editing tools. However, current image editing models based on VLMs or LLMs struggle to understand and execute edits based solely on scribble inputs. To systematically study this problem, we construct a new benchmark, ScribbleEdit, that evaluates the ability of image editing models to perform image editing conditioned on scribbles. This task requires both a deep understanding of the intention of the scribble and an accurate interpretation of its spatial information. In ScribbleEdit, we design an automated data construction pipeline and introduce a dedicated evaluation protocol that explicitly measures intention alignment. Our analysis reveals that existing VLM/LLM-based editing models fail to accurately capture scribble intentions. To guide future progress on scribble-only image editing, we propose a simple yet effective soft-token baseline, which enhances the model's understanding of scribble semantics and outperforms standard image editing models on our benchmark. Our evaluation and baseline together provide a concrete foundation for assessing and improving the scribble-driven image editing.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09382 — 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 2026-10-08T12:18:15.528Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).