DiracDiffusion：具有保证数据一致性的去噪与增量重建
DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency
- University of Southern California（南加州大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出DiracDiffusion框架，通过逆转随机退化过程恢复图像，在逆过程中保持数据一致性，并灵活权衡感知与失真指标，实现采样加速，在多个高分辨率数据集上超越现有扩散方法。
AI中文摘要：
扩散模型已在众多计算机视觉任务中确立了新的最先进水平，包括图像恢复。基于扩散的逆问题求解器能够从严重损坏的测量中生成具有卓越视觉质量的重建结果。然而，在广为人知的感知-失真权衡中，感知上吸引人的重建的代价往往是失真指标（如PSNR）的下降。失真指标衡量对观测的忠实度，这是逆问题中的关键要求。在这项工作中，我们提出了一种新的逆问题求解框架，即我们假设观测来自一个随机退化过程，该过程逐渐退化并对原始干净图像添加噪声。我们学习逆转退化过程以恢复干净图像。我们的技术在整个逆过程中保持与原始测量的一致性，并允许在感知质量与改进的失真指标之间进行灵活权衡，以及通过提前停止实现采样加速。我们在不同的高分辨率数据集和逆问题上展示了我们方法的效率，在感知和失真指标方面均取得了比其他最先进的基于扩散的方法更大的改进。
英文摘要：
Diffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. Diffusion-based inverse problem solvers generate reconstructions of exceptional visual quality from heavily corrupted measurements. However, in what is widely known as the perception-distortion trade-off, the price of perceptually appealing reconstructions is often paid in declined distortion metrics, such as PSNR. Distortion metrics measure faithfulness to the observation, a crucial requirement in inverse problems. In this work, we propose a novel framework for inverse problem solving, namely we assume that the observation comes from a stochastic degradation process that gradually degrades and noises the original clean image. We learn to reverse the degradation process in order to recover the clean image. Our technique maintains consistency with the original measurement throughout the reverse process, and allows for great flexibility in trading off perceptual quality for improved distortion metrics and sampling speedup via early-stopping. We demonstrate the efficiency of our method on different high-resolution datasets and inverse problems, achieving great improvements over other state-of-the-art diffusion-based methods with respect to both perceptual and distortion metrics.
