LucidNFT: 基于LR锚定的多奖励偏好优化用于基于流的现实世界超分辨率

中文摘要 AI 辅助

生成现实世界图像超分辨率（Real-ISR）可以从严重退化的低分辨率（LR）输入中合成视觉逼真的细节，但其随机采样导致关键失败模式难以避免：输出可能看起来清晰但不忠实于LR证据，出现语义或结构幻觉。基于偏好强化学习（RL）是自然选择，因为每个LR输入会产生一组候选修复。然而，Real-ISR的有效对齐受到三个耦合挑战的阻碍：（i）缺乏一个鲁棒于退化但对局部幻觉敏感的LR参考忠实信号；（ii）rollout组优化瓶颈，其中在归一化前标量化异质奖励会压缩目标对比度并削弱扩散NFT风格的奖励加权更新；（iii）真实退化的有限覆盖，限制了rollout多样性和偏好信号质量。我们提出LucidNFT，一种用于流匹配Real-ISR的多奖励RL框架。LucidNFT引入LucidConsistency，一种退化不变且幻觉敏感的LR参考评估器，通过内容一致的退化池和原始输入修补的硬负样本训练；一种解耦的奖励归一化策略，该策略在融合前在每个LR条件化的rollout组内保留目标对比度；以及LucidLR，一个大规模的真实世界退化图像集合用于鲁棒的RL微调。大量实验表明，LucidNFT在强大的基于流的Real-ISR基线中提升了感知质量，同时在多样化的现实世界场景中普遍保持LR参考一致性。

英文摘要

Generative real-world image super-resolution (Real-ISR) can synthesize visually convincing details from severely degraded low-resolution (LR) inputs, yet its stochastic sampling makes a critical failure mode hard to avoid: outputs may look sharp but be unfaithful to the LR evidence, exhibiting semantic or structural hallucinations. Preference-based reinforcement learning (RL) is a natural fit because each LR input yields a rollout group of candidate restorations. However, effective alignment in Real-ISR is hindered by three coupled challenges: (i) the lack of an LR-referenced faithfulness signal that is robust to degradation yet sensitive to localized hallucinations, (ii) a rollout-group optimization bottleneck where scalarizing heterogeneous rewards before normalization compresses objective-wise contrasts and weakens DiffusionNFT-style reward-weighted updates, and (iii) limited coverage of real degradations, which restricts rollout diversity and preference signal quality. We propose LucidNFT, a multi-reward RL framework for flow-matching Real-ISR. LucidNFT introduces LucidConsistency, a degradation-invariant and hallucination-sensitive LR-referenced evaluator trained with content-consistent degradation pools and original-inpainted hard negatives; a decoupled reward normalization strategy that preserves objective-wise contrasts within each LR-conditioned rollout group before fusion; and LucidLR, a large-scale collection of real-world degraded images for robust RL fine-tuning. Extensive experiments show that LucidNFT improves perceptual quality on strong flow-based Real-ISR baselines while generally maintaining LR-referenced consistency across diverse real-world scenarios.

发表机构

• The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））
• The Hong Kong University of Science and Technology（香港科学与技术大学）

机构由 AI 辅助整理，请以论文原文为准。