FED-Bench：一种跨粒度的面部表情编辑评估基准
FED-Bench: A Cross-Granular Benchmark for Disentangled Evaluation of Facial Expression Editing
AI总结：
本文提出FED-Bench，通过构建747个三元组基准，引入FED-Score评估协议，评估面部表情编辑的对齐、保真度和相对表达增益，揭示当前方法在高保真与准确表达操控间的困境，并提供20k+真实世界面部训练集。
摘要：
面部表情图像编辑需要精细控制以严格保持人类身份和背景，同时精确操控表情。然而，现有编辑基准主要关注一般场景，缺乏高质量面部图像和对应的编辑指令。此外，当前评估指标在该任务中存在系统性偏见，往往偏向懒惰编辑或过拟合编辑。为弥合这些差距，我们提出FED-Bench，一个全面的基准，包含严格测试和准确的评估套件。首先，我们通过级联和可扩展的管道精心构建了747个三元组基准，每个包含原始图像、编辑指令和地面真相图像以进行精确评估。其次，我们引入FED-Score，一种跨粒度的评估协议，将评估拆分为三个维度：对齐用于验证指令遵循，保真度用于测试图像质量和身份保持，相对表达增益用于量化表达变化的幅度，有效缓解上述评估偏见。第三，我们评估了18个图像编辑模型，发现当前方法难以同时实现高保真和准确表达操控，细粒度指令遵循被识别为主要瓶颈。最后，利用所引入基准引擎的可扩展特性，我们提供了一个20k+的现实世界面部训练集，并通过微调基线模型证明其有效性，该模型实现了显著性能提升。我们的基准及相关代码将很快公开。
英文摘要：
Facial expression image editing requires fine-grained control to strictly preserve human identity and background while precisely manipulating expression. However, existing editing benchmarks primarily focus on general scenarios, lacking high-quality facial images and corresponding editing instructions. Furthermore, current evaluation metrics exhibit systemic biases in this task, often favoring lazy editing or overfit editing. To bridge these gaps, we propose FED-Bench, a comprehensive benchmark featuring rigorous testing and an accurate evaluation suite. First, we carefully construct a benchmark of 747 triplets through a cascaded and scalable pipeline, each comprising an original image, an editing instruction, and a ground-truth image for precise evaluation. Second, we introduce FED-Score, a cross-granularity evaluation protocol that disentangles assessment into three dimensions: Alignment for verifying instruction following, Fidelity for testing image quality and identity preservation, and Relative Expression Gain for quantifying the magnitude of expression changes, effectively mitigating the aforementioned evaluation biases. Third, we benchmark 18 image editing models, revealing that current approaches struggle to simultaneously achieve high fidelity and accurate expression manipulation, with fine-grained instruction following identified as the primary bottleneck. Finally, leveraging the scalable characteristic of introduced benchmark engine, we provide a 20k+ in-the-wild facial training set and demonstrate its effectiveness by fine-tuning a baseline model that achieves significant performance gains. Our benchmark and related code will be made publicly 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。
