对恶劣天气条件下盲面修复的降级无关统计面部特征转换
Degradation-Agnostic Statistical Facial Feature Transformation for Blind Face Restoration in Adverse Weather Conditions
AI总结：
本文提出了一种基于GAN的盲面部修复框架，通过局部统计面部特征转换和降级无关特征嵌入模块，提升恶劣天气下的面部修复效果。
摘要：
随着智能闭路电视系统在户外环境中的日益普及，对优化挑战性天气条件下面部识别系统的需求日益增长。恶劣天气显著降低图像质量，从而降低识别准确性。尽管基于生成对抗网络（GANs）和扩散模型的最新面部图像修复（FIR）模型已取得进展，但其性能仍然受限于缺乏专门模块来显式处理天气引起的降级问题。这导致面部纹理和结构失真。为了解决这些限制，我们提出了一种新的基于GAN的盲FIR框架，集成了两个关键组件：局部统计面部特征转换（SFFT）和降级无关特征嵌入（DAFE）。局部SFFT模块通过将低质量（LQ）面部区域的局部统计分布与高质量（HQ）对应部分对齐，来增强面部结构和颜色保真度。互补地，DAFE模块通过将LQ和HQ编码器表示对齐，从而在恶劣天气条件下实现稳健的统计面部特征提取，使修复过程适应于严重的天气引起的降级。实验结果表明，所提出的降级无关SFFT模型在抑制纹理失真和准确重建面部结构方面优于基于GAN和扩散模型的现有最先进FIR方法。此外，SFFT和DAFE模块在增强面部修复中结构保真度和感知质量方面也得到了实证验证。
英文摘要：
With the increasing deployment of intelligent CCTV systems in outdoor environments, there is a growing demand for face recognition systems optimized for challenging weather conditions. Adverse weather significantly degrades image quality, which in turn reduces recognition accuracy. Although recent face image restoration (FIR) models based on generative adversarial networks (GANs) and diffusion models have shown progress, their performance remains limited due to the lack of dedicated modules that explicitly address weather-induced degradations. This leads to distorted facial textures and structures. To address these limitations, we propose a novel GAN-based blind FIR framework that integrates two key components: local Statistical Facial Feature Transformation (SFFT) and Degradation-Agnostic Feature Embedding (DAFE). The local SFFT module enhances facial structure and color fidelity by aligning the local statistical distributions of low-quality (LQ) facial regions with those of high-quality (HQ) counterparts. Complementarily, the DAFE module enables robust statistical facial feature extraction under adverse weather conditions by aligning LQ and HQ encoder representations, thereby making the restoration process adaptive to severe weather-induced degradations. Experimental results demonstrate that the proposed degradation-agnostic SFFT model outperforms existing state-of-the-art FIR methods based on GAN and diffusion models, particularly in suppressing texture distortions and accurately reconstructing facial structures. Furthermore, both the SFFT and DAFE modules are empirically validated in enhancing structural fidelity and perceptual quality in face restoration under challenging weather scenarios.
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。
