用生成模型先验提升运动去模糊初始核，解决敏感问题。
Generative Latent Kernel Modeling for Blind Motion Deblurring
- 用GAN训练生成器和初始化器，学习模糊核先验分布
- 在真实数据集上达到当前最好性能，尤其在非均匀模糊场景
- 可插件式接入现有方法，无需修改核心结构
基于深度先验的盲运动去模糊方法近年来表现优异，但常受优化过程高度非凸性影响，对初始模糊核极度敏感。为此，本文提出一种新框架，利用深度生成模型编码核先验，改善初始核质量。具体地，通过预训练生成对抗网络（GAN）构建核生成器，准确刻画核的先验分布，并设计核初始化器，为核估计提供高质量起始点。结合二者，将去模糊解约束于紧凑的潜在核流形中，显著缓解对初始核的敏感性。该生成器与初始化器可无缝集成至现有去模糊方法中，实现即插即用。进一步扩展至盲非均匀运动去模糊，无需额外先验，在挑战性基准数据集上取得领先效果。代码已开源。
原文摘要 · Abstract (English)
Deep prior-based approaches have demonstrated remarkable success in blind motion deblurring (BMD) recently. These methods, however, are often limited by the high non-convexity of the underlying optimization process in BMD, which leads to extreme sensitivity to the initial blur kernel. To address this issue, we propose a novel framework for BMD that leverages a deep generative model to encode the kernel prior and induce a better initialization for the blur kernel. Specifically, we pre-train a kernel generator based on a generative adversarial network (GAN) to aptly characterize the kernel's prior distribution, as well as a kernel initializer to provide a well-informed and high-quality starting point for kernel estimation. By combining these two components, we constrain the BMD solution within a compact latent kernel manifold, thus alleviating the aforementioned sensitivity for kernel initialization. Notably, the kernel generator and initializer are designed to be easily integrated with existing BMD methods in a plug-and-play manner, enhancing their overall performance. Furthermore, we extend our approach to tackle blind non-uniform motion deblurring without the need for additional priors, achieving state-of-the-art performance on challenging benchmark datasets. The source code is available at https://github.com/dch0319/GLKM-Deblur.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。