Hero-SR：面向超分辨率的、带有人类感知先验的一步扩散方法
Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priors
AI总结：
本文提出一步扩散超分框架 Hero-SR，通过 DTSM 自适应选择扩散步并利用 OWMS 经 CLIP 融合图文监督，在严重退化场景下兼顾语义一致性与感知自然性，达到 Real-SR 最先进性能。
摘要：
得益于扩散模型强大的先验，近期方法在解决真实世界超分辨率（Real-SR）问题上展现出潜力。然而，要实现语义一致性和感知自然性以满足人类感知需求仍然困难，尤其是在严重退化和输入复杂度多变的条件下。为解决这一问题，我们提出 Hero-SR，这是一个明确融入人类感知先验的基于扩散的一步式 SR 框架。Hero-SR 包含两个新颖模块：动态时间步模块（DTSM），其自适应选择最优扩散步，以灵活满足人类感知标准；以及开放世界多模态监督（OWMS），其通过 CLIP 整合来自图像和文本两个域的引导，以提升语义一致性和感知自然性。通过这些模块，Hero-SR 生成的高分辨率图像不仅保留复杂细节，还反映人类感知偏好。大量实验验证，Hero-SR 在 Real-SR 中达到最先进性能。代码将在论文被接收后公开发布。
英文摘要：
Owing to the robust priors of diffusion models, recent approaches have shown promise in addressing real-world super-resolution (Real-SR). However, achieving semantic consistency and perceptual naturalness to meet human perception demands remains difficult, especially under conditions of heavy degradation and varied input complexities. To tackle this, we propose Hero-SR, a one-step diffusion-based SR framework explicitly designed with human perception priors. Hero-SR consists of two novel modules: the Dynamic Time-Step Module (DTSM), which adaptively selects optimal diffusion steps for flexibly meeting human perceptual standards, and the Open-World Multi-modality Supervision (OWMS), which integrates guidance from both image and text domains through CLIP to improve semantic consistency and perceptual naturalness. Through these modules, Hero-SR generates high-resolution images that not only preserve intricate details but also reflect human perceptual preferences. Extensive experiments validate that Hero-SR achieves state-of-the-art performance in Real-SR. The code will be publicly available upon paper acceptance.
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。
