揭示图像超分辨率中的过度平滑挑战：基于熵的量化与对比优化
Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization
AI总结：
本文提出中心导向优化问题，用熵量化其强度，并设计细节增强对比损失显式解决，提升PSNR导向模型感知质量，在GAN方法上达到SOTA。
摘要：
面向PSNR的模型是一类关键的超分辨率模型，在各个领域都有应用。然而，这些模型倾向于生成过度平滑的图像，这一问题先前已从模型或损失函数的角度进行了分析，但未考虑数据属性的影响。在本文中，我们提出了一种新现象，称为中心导向优化（COO）问题，即模型的输出趋向于相似高分辨率图像的中心点，而非趋向于真实值。我们证明了该问题的强度与数据的不确定性相关，并使用熵对其进行量化。我们证明，随着高分辨率图像熵的增加，其中心点将远离干净图像分布，模型将生成过度平滑的图像。隐式优化COO问题可以被视为感知驱动的方法，如感知损失、模型结构优化或基于GAN的方法。我们提出了对COO问题的显式解决方案，称为细节增强对比损失（DECLoss）。DECLoss利用对比学习的聚类特性，直接降低潜在高分辨率分布的方差，从而降低熵。我们在多个超分辨率基准上评估了DECLoss，并证明它提高了面向PSNR模型的感知质量。此外，当应用于基于GAN的方法（如RaGAN）时，DECLoss有助于实现最先进的性能，例如在4倍下采样的Urban100上，LPIPS为0.093，PSNR为24.51，验证了我们方法的有效性和泛化性。
英文摘要：
PSNR-oriented models are a critical class of super-resolution models with applications across various fields. However, these models tend to generate over-smoothed images, a problem that has been analyzed previously from the perspectives of models or loss functions, but without taking into account the impact of data properties. In this paper, we present a novel phenomenon that we term the center-oriented optimization (COO) problem, where a model's output converges towards the center point of similar high-resolution images, rather than towards the ground truth. We demonstrate that the strength of this problem is related to the uncertainty of data, which we quantify using entropy. We prove that as the entropy of high-resolution images increases, their center point will move further away from the clean image distribution, and the model will generate over-smoothed images. Implicitly optimizing the COO problem, perceptual-driven approaches such as perceptual loss, model structure optimization, or GAN-based methods can be viewed. We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss). DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution and thereby decrease the entropy. We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models. Moreover, when applied to GAN-based methods, such as RaGAN, DECLoss helps to achieve state-of-the-art performance, such as 0.093 LPIPS with 24.51 PSNR on 4x downsampled Urban100, validating the effectiveness and generalization of our approach.
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。
