CVJun 1, 2022

Multi-scale frequency separation network for image deblurring

arXiv:2206.00798v359 citationsh-index: 21
Originality Incremental advance
AI Analysis

This addresses the problem of restoring detailed textures from blurry images for computer vision applications, representing an incremental improvement by focusing on frequency characteristics.

The paper tackles image deblurring by proposing a multi-scale frequency separation network (MSFS-Net) that captures low- and high-frequency information, achieving state-of-the-art performance on benchmark datasets.

Image deblurring aims to restore the detailed texture information or structures from blurry images, which has become an indispensable step in many computer vision tasks. Although various methods have been proposed to deal with the image deblurring problem, most of them treated the blurry image as a whole and neglected the characteristics of different image frequencies. In this paper, we present a new method called multi-scale frequency separation network (MSFS-Net) for image deblurring. MSFS-Net introduces the frequency separation module (FSM) into an encoder-decoder network architecture to capture the low- and high-frequency information of image at multiple scales. Then, a cycle-consistency strategy and a contrastive learning module (CLM) are respectively designed to retain the low-frequency information and recover the high-frequency information during deblurring. At last, the features of different scales are fused by a cross-scale feature fusion module (CSFFM). Extensive experiments on benchmark datasets show that the proposed network achieves state-of-the-art performance.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes