LIR: A Lightweight Baseline for Image Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Dongqi, Yue, Ting, Zhao, Xin, Xu, Renjing, Chang, Liang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911930207174656
author Fan, Dongqi
Yue, Ting
Zhao, Xin
Xu, Renjing
Chang, Liang
author_facet Fan, Dongqi
Yue, Ting
Zhao, Xin
Xu, Renjing
Chang, Liang
contents Recently, there have been significant advancements in Image Restoration based on CNN and transformer. However, the inherent characteristics of the Image Restoration task are often overlooked in many works. They, instead, tend to focus on the basic block design and stack numerous such blocks to the model, leading to parameters redundant and computations unnecessary. Thus, the efficiency of the image restoration is hindered. In this paper, we propose a Lightweight Baseline network for Image Restoration called LIR to efficiently restore the image and remove degradations. First of all, through an ingenious structural design, LIR removes the degradations existing in the local and global residual connections that are ignored by modern networks. Then, a Lightweight Adaptive Attention (LAA) Block is introduced which is mainly composed of proposed Adaptive Filters and Attention Blocks. The proposed Adaptive Filter is used to adaptively extract high-frequency information and enhance object contours in various IR tasks, and Attention Block involves a novel Patch Attention module to approximate the self-attention part of the transformer. On the deraining task, our LIR achieves the state-of-the-art Structure Similarity Index Measure (SSIM) and comparable performance to state-of-the-art models on Peak Signal-to-Noise Ratio (PSNR). For denoising, dehazing, and deblurring tasks, LIR also achieves a comparable performance to state-of-the-art models with a parameter size of about 30\%. In addition, it is worth noting that our LIR produces better visual results that are more in line with the human aesthetic.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01368
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LIR: A Lightweight Baseline for Image Restoration
Fan, Dongqi
Yue, Ting
Zhao, Xin
Xu, Renjing
Chang, Liang
Computer Vision and Pattern Recognition
Recently, there have been significant advancements in Image Restoration based on CNN and transformer. However, the inherent characteristics of the Image Restoration task are often overlooked in many works. They, instead, tend to focus on the basic block design and stack numerous such blocks to the model, leading to parameters redundant and computations unnecessary. Thus, the efficiency of the image restoration is hindered. In this paper, we propose a Lightweight Baseline network for Image Restoration called LIR to efficiently restore the image and remove degradations. First of all, through an ingenious structural design, LIR removes the degradations existing in the local and global residual connections that are ignored by modern networks. Then, a Lightweight Adaptive Attention (LAA) Block is introduced which is mainly composed of proposed Adaptive Filters and Attention Blocks. The proposed Adaptive Filter is used to adaptively extract high-frequency information and enhance object contours in various IR tasks, and Attention Block involves a novel Patch Attention module to approximate the self-attention part of the transformer. On the deraining task, our LIR achieves the state-of-the-art Structure Similarity Index Measure (SSIM) and comparable performance to state-of-the-art models on Peak Signal-to-Noise Ratio (PSNR). For denoising, dehazing, and deblurring tasks, LIR also achieves a comparable performance to state-of-the-art models with a parameter size of about 30\%. In addition, it is worth noting that our LIR produces better visual results that are more in line with the human aesthetic.
title LIR: A Lightweight Baseline for Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.01368