QualiTeacher: 基于质量条件的伪标签用于现实世界图像恢复
QualiTeacher: Quality-Conditioned Pseudo-Labeling for Real-World Image Restoration
AI总结：
QualiTeacher通过条件化伪标签质量提升图像恢复质量，解决传统方法中伪标签质量与模型泛化能力的矛盾。
摘要：
现实世界图像恢复（RWIR）是一个极具挑战性的任务，因为缺乏干净的地面真实图像。许多最近的方法依赖于伪标签（PL）监督，通常在Mean-Teacher（MT）框架内。然而，这些方法面临一个关键悖论：无条件信任通常不完美、低质量的PLs迫使学生模型学习不希望的伪影，而丢弃它们则严重限制数据多样性并损害模型泛化能力。在本文中，我们提出了QualiTeacher，一种新的框架，将伪标签质量从噪声负担转变为条件监督信号。不同于过滤，QualiTeacher明确将学生模型条件于PLs的质量，通过一组互补的非参考图像质量评估（NR-IQA）模型估算，涵盖低级失真和语义级评估。这种策略教导学生网络学习一个质量分级的恢复流形，使其能够理解不同质量水平的构成。因此，它不仅能避免模仿低质量标签的伪影，还能外推生成比教师自身更高的质量结果。为了确保质量驱动学习的鲁棒性和准确性，我们进一步增强过程，使用多增强方案来多样化PL质量谱，一种受直接偏好优化（DPO）启发的基于分数的偏好优化策略以强制质量分离的单调有序，以及裁剪一致性损失以防止对抗性过度优化（奖励黑客）的IQA模型。在标准RWIR基准上的实验表明，QualiTeacher可以作为即插即用的策略来提高现有伪标签框架的质量，建立从不完美监督学习的新范式。代码将被发布。
英文摘要：
Real-world image restoration (RWIR) is a highly challenging task due to the absence of clean ground-truth images. Many recent methods resort to pseudo-label (PL) supervision, often within a Mean-Teacher (MT) framework. However, these methods face a critical paradox: unconditionally trusting the often imperfect, low-quality PLs forces the student model to learn undesirable artifacts, while discarding them severely limits data diversity and impairs model generalization. In this paper, we propose QualiTeacher, a novel framework that transforms pseudo-label quality from a noisy liability into a conditional supervisory signal. Instead of filtering, QualiTeacher explicitly conditions the student model on the quality of the PLs, estimated by an ensemble of complementary non-reference image quality assessment (NR-IQA) models spanning low-level distortion and semantic-level assessment. This strategy teaches the student network to learn a quality-graded restoration manifold, enabling it to understand what constitutes different quality levels. Consequently, it can not only avoid mimicking artifacts from low-quality labels but also extrapolate to generate results of higher quality than the teacher itself. To ensure the robustness and accuracy of this quality-driven learning, we further enhance the process with a multi-augmentation scheme to diversify the PL quality spectrum, a score-based preference optimization strategy inspired by Direct Preference Optimization (DPO) to enforce a monotonically ordered quality separation, and a cropped consistency loss to prevent adversarial over-optimization (reward hacking) of the IQA models. Experiments on standard RWIR benchmarks demonstrate that QualiTeacher can serve as a plug-and-play strategy to improve the quality of the existing pseudo-labeling framework, establishing a new paradigm for learning from imperfect supervision. Code will be released.
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。
