arXiv 2603.036572026-03-04cs.CVcs.AI

InEdit-Bench：智能图像编辑模型中间逻辑路径的基准测试

InEdit-Bench: Benchmarking Intermediate Logical Pathways for Intelligent Image Editing Models

State Key Laboratory of Optical Field Manipulation Science and Technology, Institute of Optics and Electronics, Chinese Academy of Sciences（光学场操控科学与技术国家重点实验室，光学电子研究所，中国科学院）；National Laboratory on Adaptive Optics（自适应光学国家实验室）；University of Chinese Academy of Sciences（中国科学院大学）

Zhiqiang Sheng, Xumeng Han, Zhiwei Zhang, Zenghui Xiong, Yifan Ding, Aoxiang Ping, Xiang Li, Tong Guo, Yao Mao

备注：: CVPR findings. Project page: https://github.com/SZStrong1/InEdit-Bench

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

InEdit-Bench通过评估图像编辑模型在中间逻辑路径推理中的表现，揭示了现有模型在动态推理和多步骤演变建模方面的不足，推动更智能的多模态生成模型发展。

摘要：

多模态生成模型在图像编辑领域取得了显著进展，在各种静态任务上表现出色。然而，它们通常无法处理需要动态推理的复杂场景，这使它们难以建模从初始状态到最终状态的多步骤演变过程中的连贯中间逻辑路径。这种能力对于解锁视觉操作中的更深层次过程和因果理解至关重要。为系统测量这一关键限制，我们引入了InEdit-Bench，这是首个专门针对图像编辑中中间路径推理的评估基准。InEdit-Bench包含经过精心标注的测试用例，涵盖四个基本任务类别：状态转换、动态过程、时间序列和科学模拟。此外，为了实现细粒度评估，我们提出了一套评估标准，用于评估生成路径的逻辑连贯性和视觉自然性，以及模型对指定路径约束的忠实度。我们对14个代表性的图像编辑模型在InEdit-Bench上的全面评估揭示了该领域存在显著且广泛的问题。通过提供标准化且具有挑战性的基准，我们希望InEdit-Bench能促进研究并引导发展为更具动态性、推理能力和智能的多模态生成模型。

英文摘要：

Multimodal generative models have made significant strides in image editing, demonstrating impressive performance on a variety of static tasks. However, their proficiency typically does not extend to complex scenarios requiring dynamic reasoning, leaving them ill-equipped to model the coherent, intermediate logical pathways that constitute a multi-step evolution from an initial state to a final one. This capacity is crucial for unlocking a deeper level of procedural and causal understanding in visual manipulation. To systematically measure this critical limitation, we introduce InEdit-Bench, the first evaluation benchmark dedicated to reasoning over intermediate pathways in image editing. InEdit-Bench comprises meticulously annotated test cases covering four fundamental task categories: state transition, dynamic process, temporal sequence, and scientific simulation. Additionally, to enable fine-grained evaluation, we propose a set of assessment criteria to evaluate the logical coherence and visual naturalness of the generated pathways, as well as the model's fidelity to specified path constraints. Our comprehensive evaluation of 14 representative image editing models on InEdit-Bench reveals significant and widespread shortcomings in this domain. By providing a standardized and challenging benchmark, we aim for InEdit-Bench to catalyze research and steer development towards more dynamic, reason-aware, and intelligent multimodal generative models.

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。