Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ren, J., Kang, H., Guo, K., Yang, Y., Liu, B., Jiang, L., Yan, Q., Liu, Z., Song, Y., Xing, Y., Liu, H., & Lu, X. (2026). ScribbleEdit: A Benchmark for Scribble-Only Image Editing. https://omanscience.com/en/articles/scribbleedit-a-benchmark-for-scribble-only-image-editing
MLA 9
Ren, Jie, et al. "ScribbleEdit: A Benchmark for Scribble-Only Image Editing." https://omanscience.com/en/articles/scribbleedit-a-benchmark-for-scribble-only-image-editing.
Chicago (author–date)
Ren, Jie, Hao Kang, Kai Guo, Yiding Yang, Bo Liu, Liming Jiang, Qing Yan, Zichuan Liu, Yizhi Song, Yue Xing, Hui Liu, and Xin Lu. 2026. "ScribbleEdit: A Benchmark for Scribble-Only Image Editing." https://omanscience.com/en/articles/scribbleedit-a-benchmark-for-scribble-only-image-editing.
Harvard
Ren, J., Kang, H., Guo, K., Yang, Y., Liu, B., Jiang, L., Yan, Q., Liu, Z., Song, Y., Xing, Y., Liu, H. and Lu, X. (2026) 'ScribbleEdit: A Benchmark for Scribble-Only Image Editing', Available at: https://omanscience.com/en/articles/scribbleedit-a-benchmark-for-scribble-only-image-editing.
Vancouver
Ren J, Kang H, Guo K, Yang Y, Liu B, Jiang L, et al. ScribbleEdit: A Benchmark for Scribble-Only Image Editing. https://omanscience.com/en/articles/scribbleedit-a-benchmark-for-scribble-only-image-editing
IEEE
J. Ren, H. Kang, K. Guo, Y. Yang, B. Liu, L. Jiang, Q. Yan, Z. Liu, Y. Song, Y. Xing, H. Liu, and X. Lu, "ScribbleEdit: A Benchmark for Scribble-Only Image Editing," https://omanscience.com/en/articles/scribbleedit-a-benchmark-for-scribble-only-image-editing.