计算机科学 ›› 2023, Vol. 50 ›› Issue (6): 200-208.doi: 10.11896/jsjkx.220400288
刘哲, 梁宇栋, 李嘉莹
LIU Zhe, LIANG Yudong, LI Jiaying
摘要: 现有图像去雾方法普遍存在去雾不彻底、容易出现颜色失真等问题,基于传统深度学习模型的图像去雾方法多采用静态推理模式,在该模式下,模型对不同样本会采用同样的、固定的参数设置,从而抑制了模型的表达能力,影响图像的去雾效果。针对以上问题,文中提出了一种基于动态卷积核的自适应图像去雾算法,该算法包括编码网络、自适应特征增强网络和解码网络3个部分。文中采用动态卷积、密集残差、注意力机制设计了自适应特征增强网络,该网络主要包括动态残差组件和动态跨层特征融合组件。动态残差组件由动态密集残差模块、一个卷积层和双注意力模块构成,其中动态密集残差模块将动态卷积引入密集残差模块,同时设计了一个基于注意力的权重动态聚合子网络,动态地生成卷积核参数以达到样本自适应的目的,在减少信息丢失的同时增强了模型的表达能力;双注意力模块结合通道注意力和像素注意力,使模型更加关注图像通道之间的差异性以及雾霾分布不均匀的区域。动态跨层特征融合组件通过动态融合不同阶段的特征,来学习丰富的上下文信息,防止网络深层计算时遗忘网络的早期特征,同时极大地丰富了特征表示,有利于模型对无雾图像细节信息的恢复。在合成数据集和真实数据集上进行了大量实验,结果表明,所提方法不仅取得了较好的客观评价分数,而且重建了主观效果较好的去雾图像,超越了对比方法的性能。
中图分类号:
[1]KHAN M F,KHAN E,ABBASI Z A.Segment dependent dynamic multi-histogram equalization for image contrast enhancement[J].Digital Signal Processing,2014,25:198-223. [2]LI H,XIE W,WANG X,et al.GPU Implementation ofMulti-scale Retinex Image Enhancement Algorithm[C]//2016 IEEE/ACS 13thInternational Conference of Computer Systems and APpplications(AICCSA).IEEE,2016:1-5. [3]HE K,SUN J,TANG X.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,33(12):2341-2353. [4]CAI B,XU X,JIA K,et al.Dehazenet:An end-to-end system for single image haze removal[J].IEEE Transactions on Image Processing,2016,25(11):5187-5198. [5]REN W,LIU S,ZHANG H,et al.Single image dehazing viamulti-scale convolutional neural networks[C]//European Conference on Computer Vision.Cham:Springer,2016:154-169. [6]HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778. [7]ZHANG Y,TIAN Y,KONG Y,et al.Residual dense network for image super-resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:2472-2481. [8]ARIGELA S,ASARI V K.Enhancement of hazy color imagesusing a self-tunable transformation function[C]//International Symposium on Visual Computing.Cham:Springer,2014:578-587. [9]BERMAN D,AVIDAN S.Non-local image dehazing[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:1674-1682. [10]REN W,MA L,ZHANG J,et al.Gated fusion network for single image dehazing[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3253-3261. [11]LI B,PENG X,WANG Z,et al.Aod-net:All-in-one dehazing network[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:4770-4778. [12]ZHANG H,PATEL V M.Densely connected pyramid dehazing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3194-3203. [13]YI Q,LI J,FANG F,et al.Efficient and accurate multi-scale topological network for single image dehazing[J].IEEE Transactions on Multimedia,2021,24:3114-3128. [14]ZHANG X,JIANG R,WANG T,et al.Single image dehazing via dual-path recurrent network[J].IEEE Transactions on Image Processing,2021,30:5211-5222. [15]WU H,QU Y,LIN S,et al.Contrastive learning for compactsingle image dehazing[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:10551-10560. [16]YANG Y,WANG C,LIU R,et al.Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:2037-2046. [17]LIU H,WU Z,LI L,et al.Towards Multi-Domain Single Image Dehazing via Test-Time Training[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:5831-5840. [18]WU Z,NAGARAJAN T,KUMAR A,et al.Blockdrop:Dynamic inference paths in residual networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8817-8826. [19]YANG L,HAN Y,CHEN X,et al.Resolution adaptive net-works for efficient inference[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:2369-2378. [20]YANG B,BENDER G,LE Q V,et al.Condconv:Conditionally parameterized convolutions for efficient inference[J].Advances in Neural Information Processing Systems,2019,32:1-11. [21]MA N,ZHANG X,HUANG J,et al.Weightnet:Revisiting the design space of weight networks[C]//European Conference on Computer Vision.Springer,Cham,2020:776-792. [22] CHEN Y,DAI X,LIU M,et al.Dynamic convolution:Attention over convolution kernels[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:11030-11039. [23]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141. [24]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:3-19. [25]DOSOVITSKIY A,BEYER L,KOLESNIKOV A,et al.Animage is worth 16x16 words:Transformers for image recognition at scale[J].arXiv:2010.11929,2020. [26]GUO M H,XU T X,LIU J J,et al.Attention Mechanisms in Computer Vision:A Survey[J].arXiv:2111.07624,2021. [27]LIU X,MA Y,SHI Z,et al.Griddehazenet:Attention-basedmulti-scale network for image dehazing[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:7314-7323. [28]HONG M,XIE Y,LI C,et al.Distilling image dehazing with heterogeneous task imitation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:3462-3471. [29]QIN X,WANG Z,BAI Y,et al.FFA-Net:Feature fusion attention network for single image dehazing[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:11908-11915. [30]LI B,REN W,FU D,et al.Benchmarking single-image dehazing and beyond[J].IEEE Transactions on Image Processing,2018,28(1):492-505. [31]ANCUTI C O,ANCUTI C,TIMOFTE R.NH-HAZE:Animage dehazing benchmark with non-homogeneous hazy and haze-free images[C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition Workshops.2020:444-445. |
|