AsyncDSB：用于图像修复的调度异步扩散薛定谔桥
AsyncDSB: Schedule-Asynchronous Diffusion Schrödinger Bridge for Image Inpainting
AI总结：
针对现有扩散薛定谔桥图像修复方法中调度与修复不匹配的问题，提出像素级异步噪声调度的AsyncDSB方法，依据梯度优先级调度像素，在真实数据集上FID较SOTA提升3%-14%。
摘要：
图像修复是一项重要的图像生成任务，旨在从部分可见区域恢复受损图像。近年来，扩散薛定谔桥方法通过将受损图像与目标图像之间的转换建模为沿加噪调度路径的扩散薛定谔桥过程，有效解决了这一任务。尽管这些方法已展现出优异性能，本文发现：1）现有方法存在调度-修复不匹配问题，即理论调度与实际修复过程通常存在较大差异，从理论上导致调度未能被充分用于图像修复；2）造成该问题的关键原因是所有像素的修复过程实际上是异步的，但现有方法为它们设置了同步噪声调度，即所有像素共享相同的噪声调度。为此，我们提出了用于图像修复的调度异步扩散薛定谔桥（AsyncDSB）。我们的核心思路是优先调度高频（即大梯度）像素，再调度低频（即小梯度）像素。基于这一思路，给定一张受损图像，我们首先训练一个网络来预测其受损区域的梯度图。然后，我们将预测的图像梯度作为先验，设计了一种简单且有效的像素级异步噪声调度策略，以增强扩散薛定谔桥的性能。得益于像素级的异步调度，像素间修复过程的时间依赖性能够得到充分表征，从而实现高质量的图像修复。在真实世界数据集上的实验表明，我们的AsyncDSB取得了优异性能，尤其是在FID指标上，相比当前最优基线方法提升了约3%-14%。
英文摘要：
Image inpainting is an important image generation task, which aims to restore corrupted image from partial visible area. Recently, diffusion Schrödinger bridge methods effectively tackle this task by modeling the translation between corrupted and target images as a diffusion Schrödinger bridge process along a noising schedule path. Although these methods have shown superior performance, in this paper, we find that 1) existing methods suffer from a schedule-restoration mismatching issue, i.e., the theoretical schedule and practical restoration processes usually exist a large discrepancy, which theoretically results in the schedule not fully leveraged for restoring images; and 2) the key reason causing such issue is that the restoration process of all pixels are actually asynchronous but existing methods set a synchronous noise schedule to them, i.e., all pixels shares the same noise schedule. To this end, we propose a schedule-Asynchronous Diffusion Schrödinger Bridge (AsyncDSB) for image inpainting. Our insight is preferentially scheduling pixels with high frequency (i.e., large gradients) and then low frequency (i.e., small gradients). Based on this insight, given a corrupted image, we first train a network to predict its gradient map in corrupted area. Then, we regard the predicted image gradient as prior and design a simple yet effective pixel-asynchronous noise schedule strategy to enhance the diffusion Schrödinger bridge. Thanks to the asynchronous schedule at pixels, the temporal interdependence of restoration process between pixels can be fully characterized for high-quality image inpainting. Experiments on real-world datasets show that our AsyncDSB achieves superior performance, especially on FID with around 3% - 14% improvement over state-of-the-art baseline 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。
