arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.00752cs.CV
收藏

图表不是图像:关于科学图表编辑挑战的探讨

Charts Are Not Images: On the Challenges of Scientific Chart Editing

University of Southern California(南加州大学);Adobe Research(Adobe研究院);Texas A&M University(德克萨斯A&M大学)

Shawn Li, Ryan Rossi, Sungchul Kim, Sunav Choudhary, Franck Dernoncourt, Puneet Mathur, Zhengzhong Tu, Yue Zhao

AI总结:

本文提出FigEdit基准测试,揭示科学图表编辑中结构转换的重要性,并指出传统像素操作方法的不足。

摘要:

生成模型,如扩散模型和自回归方法,已在编辑自然图像方面展示了令人印象深刻的能力。然而,将这些工具应用于科学图表则建立在一个错误的假设上:图表不仅仅是像素的排列,而是受图形语法约束的结构化数据的视觉表示。因此,图表编辑不是像素操作任务,而是一个结构转换问题。为了解决这一根本性不匹配,我们引入了\textit{FigEdit},一个包含超过30,000个样本的大型科学图表编辑基准测试。基于真实数据,我们的基准测试以其多样性著称,涵盖10种不同的图表类型和丰富的复杂编辑指令词汇。该基准测试分为五个不同且逐步具有挑战性的任务:单次编辑、多次编辑、对话式编辑、基于视觉引导的编辑以及风格迁移。我们对一系列最先进的模型在该基准测试上的评估揭示了它们在科学图表上的表现不佳,因为它们始终无法处理有效编辑所需的底层结构转换。此外,我们的分析表明,传统评估指标(如SSIM、PSNR)在捕捉图表编辑的语义正确性方面存在局限。我们的基准测试展示了像素级操作的深刻局限,并为开发和评估未来的结构感知模型提供了坚实的基础。通过发布\textit{FigEdit}(https://github.com/adobe-research/figure-editing),我们旨在促进结构感知图表编辑的系统性进步,提供公平比较的共同基础,并鼓励未来研究那些能够理解科学图表视觉和语义层的模型。

英文摘要:

Generative models, such as diffusion and autoregressive approaches, have demonstrated impressive capabilities in editing natural images. However, applying these tools to scientific charts rests on a flawed assumption: a chart is not merely an arrangement of pixels but a visual representation of structured data governed by a graphical grammar. Consequently, chart editing is not a pixel-manipulation task but a structured transformation problem. To address this fundamental mismatch, we introduce \textit{FigEdit}, a large-scale benchmark for scientific figure editing comprising over 30,000 samples. Grounded in real-world data, our benchmark is distinguished by its diversity, covering 10 distinct chart types and a rich vocabulary of complex editing instructions. The benchmark is organized into five distinct and progressively challenging tasks: single edits, multi edits, conversational edits, visual-guidance-based edits, and style transfer. Our evaluation of a range of state-of-the-art models on this benchmark reveals their poor performance on scientific figures, as they consistently fail to handle the underlying structured transformations required for valid edits. Furthermore, our analysis indicates that traditional evaluation metrics (e.g., SSIM, PSNR) have limitations in capturing the semantic correctness of chart edits. Our benchmark demonstrates the profound limitations of pixel-level manipulation and provides a robust foundation for developing and evaluating future structure-aware models. By releasing \textit{FigEdit} (https://github.com/adobe-research/figure-editing), we aim to enable systematic progress in structure-aware figure editing, provide a common ground for fair comparison, and encourage future research on models that understand both the visual and semantic layers of scientific charts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑