BluRef: Unsupervised Image Deblurring with Dense-Matching References
It addresses the problem of image deblurring for scenarios without paired training data, making it adaptable to various applications, including low-resource devices.
The paper tackles unsupervised image deblurring by using unpaired blurred and sharp images to generate pseudo-ground truth via dense matching, achieving state-of-the-art performance.
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.