[Submitted on 27 Jan 2026 (v1), last revised 15 Oct 2026 (this version, v4)]
Authors:Hongzhu Yi, Yujia Yang, Yuanxiang Wang, Tong Li, Zhenyu Guan, Tianyu Zong, Jiahuan Chen, Chenxi Bao, Tiankun Yang, Haopeng Jin, Yixuan Yuan, Xinming Wang, Tao Yu, Ruilin Gao, Ruiwen Tao, Haijin Liang, Jin Ma, Jinwen Luo, Yeshani, Xinyu Zuo, Jungang Xu
Abstract:Image editing models can modify visual content through natural language, but editing dense documents requires precise local changes amid tightly coupled text, tables, and layout. We introduce VDE Bench, an evaluation resource for studying instruction-guided editing of Chinese and English document images. VDE Bench contains 3,506 instruction-guided image editing samples, including 1,578 text-region edits and 1,928 table-region edits. The benchmark pairs editing instructions and reference images with annotated editing regions and structured OCR outputs. Its evaluation protocol combines region-level and full-page measurements to assess textual correctness, structural fidelity, and visual content preservation. By focusing on the interaction between local edits and their surrounding document context, VDE Bench complements existing visual text editing benchmarks and provides a resource for diagnosing document-specific editing failures.
Submission history
From: Zhenyu Guan [view email]
[v1] Tue, 27 Jan 2026 16:51:05 UTC (36,024 KB)
[v2] Thu, 21 May 2026 07:55:15 UTC (30,997 KB)
[v3] Thu, 11 Jun 2026 07:53:49 UTC (30,997 KB)
[v4] Thu, 15 Oct 2026 12:17:21 UTC (32,986 KB)
