Trustworthy SR：通过扩散模型和人类反馈解决图像超分辨率中的歧义
Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedback
AI总结：
针对图像超分辨率中的歧义问题，提出利用扩散模型生成多样化解并结合人类反馈进行集成，从而在信息密集型应用中获得单一可信的高质量解决方案。
摘要：
超分辨率（SR）是一个不适定的逆问题，存在大量与给定低分辨率图像一致的可行解。各种确定性算法旨在寻找一个平衡保真度与感知质量的单一解；然而，这种权衡通常会导致视觉伪影，从而在以信息为中心的应用中带来歧义。另一方面，扩散模型（DMs）擅长生成跨越解空间的多样化可行SR图像。接下来的挑战是如何以可信的方式确定该集合中最可能的解。我们观察到，PSNR、LPIPS、DISTS等定量指标并不是解决歧义情况的可靠指标。为此，我们提出采用人类反馈，要求受试者选择少量可能的样本，并对所选样本的均值进行集成。该策略利用了DMs的高质量图像生成能力，同时认识到获得单一可信解的重要性，特别是在识别特定数字或字母等用例中，生成多个可行解可能无法带来可靠的结果。实验结果表明，与最先进的SR方法相比，我们提出的策略提供了更可信的解决方案。
英文摘要：
Super-resolution (SR) is an ill-posed inverse problem with a large set of feasible solutions that are consistent with a given low-resolution image. Various deterministic algorithms aim to find a single solution that balances fidelity and perceptual quality; however, this trade-off often causes visual artifacts that bring ambiguity in information-centric applications. On the other hand, diffusion models (DMs) excel in generating a diverse set of feasible SR images that span the solution space. The challenge is then how to determine the most likely solution among this set in a trustworthy manner. We observe that quantitative measures, such as PSNR, LPIPS, DISTS, are not reliable indicators to resolve ambiguous cases. To this effect, we propose employing human feedback, where we ask human subjects to select a small number of likely samples and we ensemble the averages of selected samples. This strategy leverages the high-quality image generation capabilities of DMs, while recognizing the importance of obtaining a single trustworthy solution, especially in use cases, such as identification of specific digits or letters, where generating multiple feasible solutions may not lead to a reliable outcome. Experimental results demonstrate that our proposed strategy provides more trustworthy solutions when compared to state-of-the art SR methods.
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。
