arXiv 2309.164942025-09-04cs.CV

基于多感受野非局部网络与新型对比正则化的精准轻量级去雾

Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization

Huanjiang Laboratory, Zhuji, P.R. China and School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, P.R.China（湖南江实验室，浙江诸暨，中国和浙江大学航空宇航学院，杭州，中国）；School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, P.R.China（浙江大学航空宇航学院，杭州，中国）；Electrical and Computer Engineering Department, Hellenic Mediterranean University, Heraklion, Crete, Greece（希腊地中海大学电气与计算机工程系，赫拉克利翁，克里特，希腊）

Zewei He, Zixuan Chen, Jinlei Li, Ziqian Lu, Xuecheng Sun, Hao Luo, Zhe-Ming Lu, Evangelos K. Markakis

备注：: submitted to the IEEE Journal for possible publication

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对图像去雾任务，提出由多流特征注意力模块、交叉非局部模块构成的轻量多感受野非局部网络，搭配聚焦细节的对比正则化，以不足150万参数量实现超越现有SOTA的去雾性能。

摘要：

近年来，基于深度学习的方法已在图像去雾领域占据主导地位。为进一步提升去雾性能，本文提出一种由多流特征注意力模块（MSFAB）和交叉非局部模块（CNLB）组成的多感受野非局部网络（MRFNLN）。我们首先为去雾任务提取更丰富的特征：具体而言，设计了包含三个不同感受野（即$1\ imes 1$、$3\ imes 3$、$5\ imes 5$）并行卷积的多流特征提取（MSFE）子模块，用于提取多尺度特征；在MSFE之后，采用注意力子模块使模型自适应聚焦于重要的通道/区域，这两个子模块共同构成了MSFAB。随后，我们设计了交叉非局部模块（CNLB），可捕获查询范围之外的长距离依赖关系：与查询分支采用相同输入源不同，键分支和值分支通过融合更多前置特征得到增强；CNLB利用空间金字塔下采样（SPDS）策略在不牺牲性能的前提下降低计算量与内存消耗，具备计算友好性。最后，本文提出一种新型的聚焦细节的对比正则化（DFCR），在专门为去雾设计的表征空间中，强调低层细节并忽略高层语义信息。综合实验结果表明，所提出的MRFNLN模型参数量不足150万，性能优于近期最先进的去雾方法。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。