AIM-Bench：通过细粒度分层控制进行情感图像操纵的基准测试与改进
AIM-Bench: Benchmarking and Improving Affective Image Manipulation via Fine-Grained Hierarchical Control
AI总结：
本文提出AIM-Bench，通过细粒度分层控制进行情感图像操纵的基准测试，改进了现有图像编辑基准的不足，提出了AIM-40k数据集并提升了模型性能。
摘要：
情感图像操纵（AIM）旨在通过有针对性的编辑激发特定情绪。当前图像编辑基准主要关注一般场景中的对象级修改，缺乏细粒度的粒度来捕捉情感维度。为弥补这一差距，我们引入了首个专门针对AIM的基准，称为AIM-Bench。该基准基于双路径情感建模方案，整合了Mikels情绪分类学与Valence-Arousal-Dominance框架，使能够实现高层语义和细粒度连续操纵。通过分层的人在回路工作流程，我们最终整理了800个高质量样本，涵盖8种情绪类别和5种编辑类型。为了有效评估性能，我们还设计了一个综合评估套件，结合基于规则和基于模型的度量标准，全面评估指令一致性、美观性和情绪表达性。广泛评估显示，当前编辑模型面临显著挑战，最值得注意的是普遍的积极偏见，这源于训练数据分布的固有不平衡。为解决这一问题，我们提出了一个可扩展的数据引擎，利用反向重绘策略构建AIM-40k，一个包含40000个样本的平衡指令微调数据集。具体而言，我们通过生成重绘增强原始情感图像，以建立高保真的地面真相，并合成具有不同情绪和配对精确指令的输入图像。在AIM-40k上微调基线模型，使整体性能提升了9.15%，证明了我们AIM-40k的有效性。我们的数据和相关代码将很快开源。
英文摘要：
Affective Image Manipulation (AIM) aims to evoke specific emotions through targeted editing. Current image editing benchmarks primarily focus on object-level modifications in general scenarios, lacking the fine-grained granularity to capture affective dimensions. To bridge this gap, we introduce the first benchmark designed for AIM termed AIM-Bench. This benchmark is built upon a dual-path affective modeling scheme that integrates the Mikels emotion taxonomy with the Valence-Arousal-Dominance framework, enabling high-level semantic and fine-grained continuous manipulation. Through a hierarchical human-in-the-loop workflow, we finally curate 800 high-quality samples covering 8 emotional categories and 5 editing types. To effectively assess performance, we also design a composite evaluation suite combining rule-based and model-based metrics to holistically assess instruction consistency, aesthetics, and emotional expressiveness. Extensive evaluations reveal that current editing models face significant challenges, most notably a prevalent positivity bias, which stemming from inherent imbalances in training data distribution. To tackle this, we propose a scalable data engine utilizing an inverse repainting strategy to construct AIM-40k, a balanced instruction-tuning dataset comprising 40k samples. Concretely, we enhance raw affective images via generative redrawing to establish high-fidelity ground truths, and synthesize input images with divergent emotions and paired precise instructions. Fine-tuning a baseline model on AIM-40k yields a 9.15% relative improvement in overall performance, demonstrating the effectiveness of our AIM-40k. Our data and related code will be made open soon.
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。
