DSL-FIQA：通过双集合退化学习和关键点引导Transformer评估人脸图像质量
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer
AI总结：
本文提出DSL-FIQA，结合双集合退化表征学习与人脸关键点引导Transformer，并构建平衡多样的CGFIQA-40k数据集，显著提升通用人脸图像质量评估性能。
摘要：
通用人脸图像质量评估（GFIQA）用于评价人脸图像的感知质量，这对于改进图像复原算法以及为下游任务选择高质量人脸图像至关重要。我们提出了一种新颖的基于Transformer的GFIQA方法，该方法由两个独特机制辅助。首先，双集合退化表征学习（DSL）机制使用同时具有合成退化和真实退化的人脸图像，将退化与内容解耦，从而确保对真实场景的泛化能力。这种自监督方法在全局尺度上学习退化特征，为在退化学习中使用局部图像块信息的传统方法提供了一种稳健替代方案。其次，我们的Transformer利用人脸关键点，在评估人脸图像感知质量时强调视觉显著部分。我们还引入了一个平衡且多样的Comprehensive Generic Face IQA（CGFIQA-40k）数据集，包含40K张图像，经过精心设计以克服现有数据集中的偏差，尤其是肤色和性别表征方面的不平衡。大量分析和评估证明了我们方法的稳健性，标志着相较以往方法取得了显著提升。
英文摘要：
Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel transformer-based method for GFIQA, which is aided by two unique mechanisms. First, a Dual-Set Degradation Representation Learning (DSL) mechanism uses facial images with both synthetic and real degradations to decouple degradation from content, ensuring generalizability to real-world scenarios. This self-supervised method learns degradation features on a global scale, providing a robust alternative to conventional methods that use local patch information in degradation learning. Second, our transformer leverages facial landmarks to emphasize visually salient parts of a face image in evaluating its perceptual quality. We also introduce a balanced and diverse Comprehensive Generic Face IQA (CGFIQA-40k) dataset of 40K images carefully designed to overcome the biases, in particular the imbalances in skin tone and gender representation, in existing datasets. Extensive analysis and evaluation demonstrate the robustness of our method, marking a significant improvement over prior methods.
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。
