Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: He, Zewei, Chen, Zixuan, Li, Jinlei, Lu, Ziqian, Sun, Xuecheng, Luo, Hao, Lu, Zhe-Ming, Markakis, Evangelos K.
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2309.16494
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916932274356224
author He, Zewei
Chen, Zixuan
Li, Jinlei
Lu, Ziqian
Sun, Xuecheng
Luo, Hao
Lu, Zhe-Ming
Markakis, Evangelos K.
author_facet He, Zewei
Chen, Zixuan
Li, Jinlei
Lu, Ziqian
Sun, Xuecheng
Luo, Hao
Lu, Zhe-Ming
Markakis, Evangelos K.
contents Recently, deep learning-based methods have dominated image dehazing domain. A multi-receptive-field non-local network (MRFNLN) consisting of the multi-stream feature attention block (MSFAB) and the cross non-local block (CNLB) is presented in this paper to further enhance the performance. We start with extracting richer features for dehazing. Specifically, a multi-stream feature extraction (MSFE) sub-block, which contains three parallel convolutions with different receptive fields (i.e., $1\times 1$, $3\times 3$, $5\times 5$), is designed for extracting multi-scale features. Following MSFE, an attention sub-block is employed to make the model adaptively focus on important channels/regions. These two sub-blocks constitute our MSFAB. Then, we design a cross non-local block (CNLB), which can capture long-range dependencies beyond the query. Instead of the same input source of query branch, the key and value branches are enhanced by fusing more preceding features. CNLB is computation-friendly by leveraging a spatial pyramid down-sampling (SPDS) strategy to reduce the computation and memory consumption without sacrificing the performance. Last but not least, a novel detail-focused contrastive regularization (DFCR) is presented by emphasizing the low-level details and ignoring the high-level semantic information in a representation space specially designed for dehazing. Comprehensive experimental results demonstrate that the proposed MRFNLN model outperforms recent state-of-the-art dehazing methods with less than 1.5 Million parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2309_16494
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
He, Zewei
Chen, Zixuan
Li, Jinlei
Lu, Ziqian
Sun, Xuecheng
Luo, Hao
Lu, Zhe-Ming
Markakis, Evangelos K.
Computer Vision and Pattern Recognition
Recently, deep learning-based methods have dominated image dehazing domain. A multi-receptive-field non-local network (MRFNLN) consisting of the multi-stream feature attention block (MSFAB) and the cross non-local block (CNLB) is presented in this paper to further enhance the performance. We start with extracting richer features for dehazing. Specifically, a multi-stream feature extraction (MSFE) sub-block, which contains three parallel convolutions with different receptive fields (i.e., $1\times 1$, $3\times 3$, $5\times 5$), is designed for extracting multi-scale features. Following MSFE, an attention sub-block is employed to make the model adaptively focus on important channels/regions. These two sub-blocks constitute our MSFAB. Then, we design a cross non-local block (CNLB), which can capture long-range dependencies beyond the query. Instead of the same input source of query branch, the key and value branches are enhanced by fusing more preceding features. CNLB is computation-friendly by leveraging a spatial pyramid down-sampling (SPDS) strategy to reduce the computation and memory consumption without sacrificing the performance. Last but not least, a novel detail-focused contrastive regularization (DFCR) is presented by emphasizing the low-level details and ignoring the high-level semantic information in a representation space specially designed for dehazing. Comprehensive experimental results demonstrate that the proposed MRFNLN model outperforms recent state-of-the-art dehazing methods with less than 1.5 Million parameters.
title Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.16494