用无配对图像生成伪真值，实现无需标注的图像去模糊
BluRef: Unsupervised Image Deblurring with Dense-Matching References
- 通过密集匹配找到模糊图与清晰参考图的对应关系，自动生成伪标签
- 不依赖成对训练数据，可适配不同规模模型，包括低资源设备
- 在多个基准上达到顶尖性能，为无监督去模糊提供新思路
本文提出一种新颖的无监督图像去模糊方法，其训练数据收集过程简单高效。该方法无需精心配对的模糊与清晰图像对，而是利用相似场景的未配对模糊图和清晰图，通过密集匹配模型识别模糊图与参考清晰图之间的对应关系，从而生成伪真值数据。由于训练数据获取方式简便，该方法不依赖现有配对数据或预训练网络，因而更适用于多种场景，且可适配不同规模的网络，包括面向低资源设备的设计。实验表明，该方法取得了当前最优性能，显著推动了图像去模糊领域的发展。
原文摘要 · Abstract (English)
This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring.
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。