发表机构
ByteDance（字节跳动）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对野生UGC增强图像的异常感知问题，定义了UEAP任务，构建了UEAP-4k数据集，提出DFAP-UGC方法及LADTP训练策略，实验表明其性能优于基线方法。
AI 中文摘要
图像增强与修复已成为短视频及社交媒体平台的标准后端操作，用于提升UGC视觉体验，但这些过程不可避免地引入视觉异常，尤其是在人脸、文本和纹理区域，直接损害感知保真度与观看者信任。现有图像质量评估（IQA）方法在经典失真上表现良好，不过它们针对整体质量评估，无法捕捉真实UGC中增强算法导致的特定局部异常。为填补这一空白，本文正式定义了一项新任务——UGC图像增强的质量异常感知（UEAP），并贡献了首个UEAP基准数据集，命名为UEAP-4k，该数据集从真实业务场景中整理而来，提供了异常类别、定位及严重程度级别的细粒度标注。此外，本文提出了针对野生UGC增强图像的差异融合异常感知方法（DFAP-UGC），该方法利用显式问题参考差异融合，结合密集空间查询、区域验证和质量感知排序，实现了具有挑战性场景下的鲁棒异常识别。为处理该新任务中子任务的固有耦合问题，本文提出了 locality-aware 动态任务优先级（LADTP）训练策略，可实现有效的端到端学习并消除多阶段开销。大量实验表明，本文方法在该任务上优于从经典方法适配的基线，验证了该数据集的价值及DFAP-UGC在鲁棒UGC增强图像异常感知方面的优越性，代码与数据将公开。
英文摘要
Image enhancement and restoration have become standard back-end operations on short-video and social media platforms to boost UGC visual experience. Yet these processes inevitably introduce visual anomalies--especially in faces, texts, and textures--that directly undermine perceptual fidelity and viewer trust. While existing IQA methods perform well on classic distortions, they target holistic quality assessment and fail to capture the specific, localized anomalies caused by enhancement algorithms in real-world UGC. To bridge this gap, we formally define a new task-quality Anomaly Perception for UGC image Enhancement (UEAP), and contribute the first UEAP benchmark dataset, named UEAP-4k, curated from the real business scenarios. It provides fine-grained annotations for anomaly categories, localization and severity levels. Furthermore, we propose a Difference-Fusion Anomaly Perception Method (DFAP-UGC) for wild UGC-enhanced images, which leverages explicit problem-reference difference fusion with dense spatial querying, regional verification, and quality-aware ranking, enabling robust anomaly identification in challenging scenarios. To handle the inherent coupling of subtasks in this new task, we propose a Locality-Aware Dynamic Task Prioritization (LADTP) training strategy that enables effective end-to-end learning and eliminates multi-stage overhead. Extensive experiments show that our method outperforms baselines adapted from classical approaches for this task, validating the value of this dataset and the superior of DFAP-UGC for robust UGC-enhanced image anomaly perception. Code and data will be public.
