感知优化与评估之间的意外不对称性

摘要

感知优化主要由保真度目标驱动，该目标同时强化了语义一致性和整体视觉真实感，而对抗性目标则通过增强感知锐度和精细细节提供补充性优化。尽管它们处于核心地位，但作为优化目标的有效性与作为图像质量评估（IQA）指标的能力之间的关联仍未被充分探索。在本研究中，我们进行了系统性分析，揭示了感知优化与评估之间一种意想不到的不对称性：在IQA中表现出色的保真度指标未必适用于感知优化，这种不一致性在对抗训练下尤为明显。此外，尽管判别器在优化过程中能有效抑制伪影，但其学习到的表征在作为IQA模型的主干初始化时提供的益处有限。除了这种不对称性，我们的发现进一步表明，判别器设计在塑造优化过程中起着决定性作用，其中基于局部块和卷积架构的判别器比传统或基于Transformer的替代方案能更忠实地重建细节。这些见解深化了我们对损失函数设计及其与IQA可迁移性关系的理解，为更系统化的感知优化方法铺平了道路。

English

Perceptual optimization is primarily driven by the fidelity objective, which enforces both semantic consistency and overall visual realism, while the adversarial objective provides complementary refinement by enhancing perceptual sharpness and fine-grained detail. Despite their central role, the correlation between their effectiveness as optimization objectives and their capability as image quality assessment (IQA) metrics remains underexplored. In this work, we conduct a systematic analysis and reveal an unanticipated asymmetry between perceptual optimization and assessment: fidelity metrics that excel in IQA are not necessarily effective for perceptual optimization, with this misalignment emerging more distinctly under adversarial training. In addition, while discriminators effectively suppress artifacts during optimization, their learned representations offer only limited benefits when reused as backbone initializations for IQA models. Beyond this asymmetry, our findings further demonstrate that discriminator design plays a decisive role in shaping optimization, with patch-level and convolutional architectures providing more faithful detail reconstruction than vanilla or Transformer-based alternatives. These insights advance the understanding of loss function design and its connection to IQA transferability, paving the way for more principled approaches to perceptual optimization.

感知优化与评估之间的意外不对称性

The Unanticipated Asymmetry Between Perceptual Optimization and Assessment

摘要

Support