[1]ZHENG Zhuoran,WEI Yiwen,JIA Xiuyi.UHD image dehazing method based on global and local aware networks[J].CAAI Transactions on Intelligent Systems,2024,19(1):89-96.[doi:10.11992/tis.202304013]
Copy

UHD image dehazing method based on global and local aware networks

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 19 Number of periods: 2024 1 Page number: 89-96 Column: 学术论文—机器感知与模式识别 Public date: 2024-01-05
Title:
UHD image dehazing method based on global and local aware networks
Author(s):
ZHENG Zhuoran;  WEI Yiwen;  JIA Xiuyi
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
Keywords:
image dehazing; UHD image; multilayer perceptron; spatial topology information; local feature extraction; global feature extraction; deep learning; real-time image dehazing
CLC:
TP181
DOI:
10.11992/tis.202304013
Abstract:
Current multilayer perceptron (MLP)-based models usually require flattening pixels on an image and subsequently enforce a self-attention mechanism or “Mix” enhancement scheme to achieve global modeling of images and obtain long-range dependence of the image. However, these approaches generally consume considerable computing resources to bridge the loss of spatial topological information in image reconstruction. Particularly for UHD image dehazing tasks, numerous stacked MLP models suffer from memory overflow when running a UHD-hazed image on a resource-constrained device. A novel model for real-time dehazing of 4 K images on a single GPU (110 fps) is proposed here to address this issue. This model is advantageous because it maintains spatial information of the raw image and has low computational complexity.
References:
[1] ZHENG Zhuoran, REN Wenqi, CAO Xiaochun, et al. Ultra-high-definition image dehazing via multi-guided bilateral learning[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 16180?16189.
[2] TAN R T. Visibility in bad weather from a single image[C]//2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008: 1?8.
[3] HE Kaiming, SUN Jian, TANG Xiaoou. Single image haze removal using dark channel prior[J]. IEEE transactions on pattern analysis and machine intelligence, 2011, 33(12): 2341–2353.
[4] ZHU Qingsong, MAI Jiaming, SHAO Ling. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE transactions on image processing:a publication of the IEEE signal processing society, 2015, 24(11): 3522–3533.
[5] BERMAN D, TREIBITZ T, AVIDAN S. Non-local image dehazing[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 1674?1682.
[6] 陈珂, 柯文德, 许波, 等. 改进的彩色图像去雾效果评价方法[J]. 智能系统学报, 2015, 10(5): 803–809
CHEN Ke, KE Wende, XU Bo, et al. An improved assessment method for the color image defogging effect[J]. CAAI transactions on intelligent systems, 2015, 10(5): 803–809
[7] CAI Bolun, XU Xiangmin, JIA Kui, et al. DehazeNet: an end-to-end system for single image haze removal[J]. IEEE transactions on image processing:a publication of the IEEE signal processing society, 2016, 25(11): 5187–5198.
[8] LI Boyi, PENG Xiulian, WANG Zhangyang, et al. AOD-net: all-in-one dehazing network[C]//2017 IEEE International Conference on Computer Vision. Venice: IEEE, 2017: 4780?4788.
[9] REN Wenqi, PAN Jinshan, ZHANG Hua, et al. Single image dehazing via multi-scale convolutional neural networks with holistic edges[J]. International journal of computer vision, 2020, 128(1): 240–259.
[10] DENG Zijun, ZHU Lei, HU Xiaowei, et al. Deep multi-model fusion for single-image dehazing[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2020: 2453?2462.
[11] GANDELSMAN Y, SHOCHER A, IRANI M. “double-DIP”: unsupervised image decomposition via coupled deep-image-priors[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 11018?11027.
[12] HONG Ming, XIE Yuan, LI Cuihua, et al. Distilling image dehazing with heterogeneous task imitation[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 3459?3468.
[13] LI Runde, PAN Jinshan, LI Zechao, et al. Single image dehazing via conditional generative adversarial network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 8202?8211.
[14] QU Yanyun, CHEN Yizi, HUANG Jingying, et al. Enhanced Pix2pix dehazing network[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 8152?8160.
[15] ZHANG He, PATEL V M. Densely connected pyramid dehazing network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 3194?3203.
[16] CHEN Zeyuan, WANG Yangchao, YANG Yang, et al. PSD: principled synthetic-to-real dehazing guided by physical priors[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 7176?7185.
[17] LIANG Jingyun, CAO Jiezhang, SUN Guolei, et al. SwinIR: image restoration using swin transformer[C]//2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal: IEEE, 2021: 1833?1844.
[18] YANG Fuzhi, YANG Huan, FU Jianlong, et al. Learning texture transformer network for image super-resolution[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 5790?5799.
[19] LUTHRA A, SULAKHE H, MITTAL T, et al. Eformer: edge enhancement based transformer for medical image denoising[EB/OL]. (2021?09?06)[2023?04?07]. https://arxiv.org/abs/2109.08044.
[20] CHEN Hanting, WANG Yunhe, GUO Tianyu, et al. Pre-trained image processing transformer[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 12294?12305.
[21] CHEN Xiang, LI Hao, LI Mingqiang, et al. Learning A sparse transformer network for effective image deraining[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 5896?5905.
[22] WANG Zhendong, CUN Xiaodong, BAO Jianmin, et al. Uformer: a general U-shaped transformer for image restoration[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 17662?17672.
[23] CHEN Dongdong, HE Mingming, FAN Qingnan, et al. Gated context aggregation network for image dehazing and deraining[C]//2019 IEEE Winter Conference on Applications of Computer Vision. Waikoloa: IEEE, 2019: 1375?1383.
[24] DAS S D, DUTTA S. Fast deep multi-patch hierarchical network for nonhomogeneous image dehazing[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Seattle: IEEE, 2020: 1994?2001.
[25] MEI Kangfu, JIANG Aiwen, LI Juncheng, et al. Progressive feature fusion network for realistic image dehazing[C]//Asian Conference on Computer Vision. Cham: Springer, 2019: 203?215.
[26] TOLSTIKHIN I, HOULSBY N, KOLESNIKOV A, et al. MLP-mixer: an all-MLP architecture for vision[EB/OL]. (2021?05?30)[2023?04?07]. https://arxiv.org/abs/2105.01601.pdf.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems