Charts Are Not Images: On the Challenges of Scientific Chart Editing
- URL: http://arxiv.org/abs/2512.00752v1
- Date: Sun, 30 Nov 2025 06:13:48 GMT
- Title: Charts Are Not Images: On the Challenges of Scientific Chart Editing
- Authors: Shawn Li, Ryan Rossi, Sungchul Kim, Sunav Choudhary, Franck Dernoncourt, Puneet Mathur, Zhengzhong Tu, Yue Zhao,
- Abstract summary: textitFigEdit is a benchmark for scientific figure editing comprising over 30,000 samples.<n>Our benchmark demonstrates the profound limitations of pixel-level manipulation.<n>By releasing textitFigEdit, we aim to enable systematic progress in structure-aware figure editing.
- Score: 66.38730113476677
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing [64.65742943745866]
ChartE$3$ is an End-to-End Chart Editing benchmark.<n>It directly evaluates models without relying on intermediate natural language programs or code-level supervision.<n>It contains over 1,200 high-quality samples constructed via a well-designed data pipeline with human curation.
arXiv Detail & Related papers (2026-01-29T13:29:27Z) - ChartEditor: A Reinforcement Learning Framework for Robust Chart Editing [46.847377471580366]
We present ChartEditVista, a comprehensive benchmark consisting of 7,964 samples spanning 31 chart categories.<n>The inputs in ChartEditVista include only the original chart image and natural language editing instructions, without the original chart codes.<n>We also present ChartEditor, a model trained using a reinforcement learning framework that incorporates a novel rendering reward to simultaneously enforce code executability and visual fidelity.
arXiv Detail & Related papers (2025-11-19T09:27:37Z) - SpotEdit: Evaluating Visually-Guided Image Editing Methods [3.5066378196008636]
SpotEdit is a comprehensive benchmark designed to assess visually-guided image editing methods.<n>Our benchmark includes a dedicated component on hallucination, highlighting how leading models, such as GPT-4o, often hallucinate the existence of a visual cue and erroneously perform the editing task.
arXiv Detail & Related papers (2025-08-25T16:08:57Z) - Image Editing As Programs with Diffusion Models [69.05164729625052]
We introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture.<n>IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations.<n>Our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions.
arXiv Detail & Related papers (2025-06-04T16:57:24Z) - Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions [20.617718631292696]
We develop a novel paradigm for instruction-driven image editing that leverages widely available and enormous text-image pairs.<n>Our approach introduces a multi-scale learnable region to localize and guide the editing process.<n>By treating the alignment between images and their textual descriptions as supervision and learning to generate task-specific editing regions, our method achieves high-fidelity, precise, and instruction-consistent image editing.
arXiv Detail & Related papers (2025-05-25T22:40:59Z) - GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing [60.66800567924348]
We introduce a new benchmark designed to evaluate text-guided image editing models.<n>The benchmark includes over 1000 high-quality editing examples across 20 diverse content categories.<n>We conduct a large-scale study comparing GPT-Image-1 against several state-of-the-art editing models.
arXiv Detail & Related papers (2025-05-16T17:55:54Z) - Graph Edit Distance Reward: Learning to Edit Scene Graph [69.39048809061714]
We propose a new method to edit the scene graph according to the user instructions, which has never been explored.
To be specific, in order to learn editing scene graphs as the semantics given by texts, we propose a Graph Edit Distance Reward.
In the context of text-editing image retrieval, we validate the effectiveness of our method in CSS and CRIR dataset.
arXiv Detail & Related papers (2020-08-15T04:52:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.