Multi-Depth Branch Network for Efficient Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Huiyuan, Zhang, Li, Li, Shijian, Yao, Min, Pan, Gang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929209429983232
author Tian, Huiyuan
Zhang, Li
Li, Shijian
Yao, Min
Pan, Gang
author_facet Tian, Huiyuan
Zhang, Li
Li, Shijian
Yao, Min
Pan, Gang
contents A longstanding challenge in Super-Resolution (SR) is how to efficiently enhance high-frequency details in Low-Resolution (LR) images while maintaining semantic coherence. This is particularly crucial in practical applications where SR models are often deployed on low-power devices. To address this issue, we propose an innovative asymmetric SR architecture featuring Multi-Depth Branch Module (MDBM). These MDBMs contain branches of different depths, designed to capture high- and low-frequency information simultaneously and efficiently. The hierarchical structure of MDBM allows the deeper branch to gradually accumulate fine-grained local details under the contextual guidance of the shallower branch. We visualize this process using feature maps, and further demonstrate the rationality and effectiveness of this design using proposed novel Fourier spectral analysis methods. Moreover, our model exhibits more significant spectral differentiation between branches than existing branch networks. This suggests that MDBM reduces feature redundancy and offers a more effective method for integrating high- and low-frequency information. Extensive qualitative and quantitative evaluations on various datasets show that our model can generate structurally consistent and visually realistic HR images. It achieves state-of-the-art (SOTA) results at a very fast inference speed. Our code is available at https://github.com/thy960112/MDBN.
format Preprint
id arxiv_https___arxiv_org_abs_2309_17334
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-Depth Branch Network for Efficient Image Super-Resolution
Tian, Huiyuan
Zhang, Li
Li, Shijian
Yao, Min
Pan, Gang
Image and Video Processing
Computer Vision and Pattern Recognition
A longstanding challenge in Super-Resolution (SR) is how to efficiently enhance high-frequency details in Low-Resolution (LR) images while maintaining semantic coherence. This is particularly crucial in practical applications where SR models are often deployed on low-power devices. To address this issue, we propose an innovative asymmetric SR architecture featuring Multi-Depth Branch Module (MDBM). These MDBMs contain branches of different depths, designed to capture high- and low-frequency information simultaneously and efficiently. The hierarchical structure of MDBM allows the deeper branch to gradually accumulate fine-grained local details under the contextual guidance of the shallower branch. We visualize this process using feature maps, and further demonstrate the rationality and effectiveness of this design using proposed novel Fourier spectral analysis methods. Moreover, our model exhibits more significant spectral differentiation between branches than existing branch networks. This suggests that MDBM reduces feature redundancy and offers a more effective method for integrating high- and low-frequency information. Extensive qualitative and quantitative evaluations on various datasets show that our model can generate structurally consistent and visually realistic HR images. It achieves state-of-the-art (SOTA) results at a very fast inference speed. Our code is available at https://github.com/thy960112/MDBN.
title Multi-Depth Branch Network for Efficient Image Super-Resolution
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.17334