Filters








715 Hits in 7.0 sec

Underwater Image Restoration via Contrastive Learning and a Real-world Dataset [article]

Junlin Han, Mehrdad Shoeiby, Tim Malthus, Elizabeth Botha, Janet Anstee, Saeed Anwar, Ran Wei, Mohammad Ali Armin, Hongdong Li, Lars Petersson
2021 arXiv   pre-print
To address this gap, we have constructed a large-scale real underwater image dataset, dubbed 'HICRD' (Heron Island Coral Reef Dataset), for the purpose of benchmarking existing methods and supporting the  ...  Our proposed method leveraged contrastive learning and generative adversarial networks to maximize the mutual information between raw and restored images.  ...  Phillip Ford (Ocean & Atmosphere, CSIRO) for editing and reviewing the manuscript.  ... 
arXiv:2106.10718v1 fatcat:5hljepmuibdojj2kuvvgoawei4

Underwater Image Restoration via Contrastive Learning and a Real-World Dataset

Junlin Han, Mehrdad Shoeiby, Tim Malthus, Elizabeth Botha, Janet Anstee, Saeed Anwar, Ran Wei, Mohammad Ali Armin, Hongdong Li, Lars Petersson
2022 Remote Sensing  
To address this gap, we constructed a large-scale real underwater image dataset, dubbed Heron Island Coral Reef Dataset ('HICRD'), for the purpose of benchmarking existing methods and supporting the development  ...  Our proposed method leveraged contrastive learning and generative adversarial networks to maximize the mutual information between raw and restored images.  ...  Lacking a large-scale, publicly available real-world underwater image restoration dataset with scientifically restored images limits the development of learning-based underwater image restoration methods  ... 
doi:10.3390/rs14174297 fatcat:xpg3n5xtp5hyjc74awlll7mlgq

Underwater Image Restoration Based on Convolutional Neural Network

Yan Hu, Keyan Wang, Xi Zhao, Hui Wang, Yunsong Li
2018 Asian Conference on Machine Learning  
Experimental results of synthetic and real images demonstrate that our restored underwater images exhibits more natural color correction and better visibility improvement against these state-of-the-art  ...  By learning the relationship between the underwater scenes and their corresponding blue channel transmission map and global ambient light respectively, we can recover and enhance the underwater images  ...  Acknowledgments This work was jointly supported by the National Natural Science Foundation of China (No. 61301291) and the 111 Project (B08038).  ... 
dblp:conf/acml/HuWZWL18 fatcat:wxfoyszepnhvppofvcbgo7l2qq

Underwater Image Restoration Based on a Parallel Convolutional Neural Network

Keyan Wang, Yan Hu, Jun Chen, Xianyun Wu, Xi Zhao, Yunsong Li
2019 Remote Sensing  
Experimental results based on synthetic and real images demonstrate that our restored underwater images exhibit more natural color correction and better visibility improvement against several state-of-the-art  ...  Moreover, we develop a new underwater image synthesizing method for building the training datasets, which can simulate images captured in various underwater environments.  ...  A higher UCIQE score represents a better image quality. We use 50 real-world images with diverse underwater environments as a test dataset.  ... 
doi:10.3390/rs11131591 fatcat:k727hrcapbbzneujn3gre6e7ly

Domain Adaptation for Underwater Image Enhancement via Content and Style Separation [article]

Yu-Wei Chen, Soo-Chang Pei
2022 arXiv   pre-print
i.e. synthesis, real-world underwater and clean domain, and process domain adaptation and image enhancement in latent space.  ...  To solve this problem, we propose a domain adaptation framework for underwater image enhancement via content and style separation, different from prior works of domain adaptation for underwater image enhancement  ...  synthetic and real-world underwater image, a latent transform unit, a generator and a discriminator.  ... 
arXiv:2202.08537v2 fatcat:yfnvx2t7wzdjzkmwaqwc4y5444

Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images [article]

Yan Kai, Liang Lanyue, Zheng Ziqiang, Wang Guoqing, Yang Yang
2022 arXiv   pre-print
The existing underwater enhancement methods that aim to promote the underwater visibility, heavily suffer from the poor image restoration performance and generalization ability.  ...  We formulate the interaction between the underwater visual images and the transmission map to obtain better enhancement results.  ...  the real-world underwater images.  ... 
arXiv:2203.09414v2 fatcat:n45aoz6cgra6togy42mg4qkhg4

Unsupervised Underwater Image Restoration: From a Homology Perspective

Zhenqi Fu, Huangxing Lin, Yan Yang, Shu Chai, Liyan Sun, Yue Huang, Xinghao Ding
2022 AAAI Conference on Artificial Intelligence  
In this paper, we propose an UnSupervised Underwater Image Restoration method (USUIR) by leveraging the homology property between a raw underwater image and a re-degraded image.  ...  It remains challenging to restore such degraded images using deep neural networks since real-world paired data is scarcely available while synthetic paired data cannot approximate real-world data perfectly  ...  , Fundamental Research Funds for the Central Universities 20720200003, and Tencent Open Fund.  ... 
dblp:conf/aaai/FuLYCS0D22 fatcat:dl7bg4txpjfnbhrwmm4rlwpplm

Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement [article]

Yuan Zhou, Kangming Yan
2020 arXiv   pre-print
To address this problem, we propose a new robust adversarial learning framework via physics model based feedback control and domain adaptation mechanism for enhancing underwater images to get realistic  ...  Final enhanced results on synthetic and real underwater images demonstrate the superiority of the proposed method, which outperforms nondeep and deep learning methods in both qualitative and quantitative  ...  V User study on real-world underwater image dataset.  ... 
arXiv:2002.09315v1 fatcat:defskznpbjahlnjsuqi4qhgf3q

Dilated Generative Adversarial Networks for Underwater Image Restoration

Jao-Chuan Lin, Chih-Bin Hsu, Jen-Chun Lee, Chung-Hsien Chen, Te-Ming Tu
2022 Journal of Marine Science and Engineering  
Underwater images often come with blurriness, lack of contrast, and low saturation due to the physics of light propagation, absorption, and scattering in seawater.  ...  We conduct several comparisons and demonstrate via full-reference and nonreference metrics that the proposed approach is able to simultaneously improve clarity and correct color and restores the visual  ...  We go through an evaluation and comparison on the performance of the proposed architecture on two different datasets (containing both enhanced and real-world underwater image pairs).  ... 
doi:10.3390/jmse10040500 fatcat:hi3tosdp2rfrbhtyjvqadociau

Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images

Kai Yan, Lanyue Liang, Ziqiang Zheng, Guoqing Wang, Yang Yang
2022 Applied Sciences  
The existing underwater enhancement methods that aim to promote underwater visibility heavily suffer from poor image restoration performance and generalization ability.  ...  from underwater images.  ...  for restoring the real-world underwater images.  ... 
doi:10.3390/app12115420 fatcat:5qsohrwqrzevjp4brdxe7hm2ge

Multi-purpose Oriented Real-world Underwater Image Enhancement

Zetian Mi, Yuanyuan Li, Yafei Wang, Xianping Fu
2020 IEEE Access  
and complex real-world underwater scenes.  ...  Herein, a novel multi-purpose oriented approach for real-world underwater image enhancement is proposed.  ...  [11] construct a large scale real-world underwater image enhancement benchmark dataset (UIEBD), which contains totally 950 real-world underwater images for further research. III.  ... 
doi:10.1109/access.2020.3002883 fatcat:5yovnqghibf3zosv3qoipmqoe4

Underwater image enhancement via LBP‐based attention residual network

ZhiXiong Huang, Jinjiang Li, Zhen Hua
2021 IET Image Processing  
Owing to the influence of light absorption and scattering in underwater environments, underwater images exhibit color deviation, low contrast and detail blur, and other degradations.  ...  The network consists of three modules: a color correction module to remove the color deviation in underwater images, detail repair module to restore the integrity of details, and an LBP auxiliary enhancement  ...  ACKNOWLEDGEMENTS The authors acknowledge the National Natural Science Foundation of China (Grant Nos. 61772319, 62002200, 61976125, 61976124 and 12001327), and Shandong Natural Science Foundation of China  ... 
doi:10.1049/ipr2.12341 fatcat:aessorukkbdi5k2kb2hyh3orb4

Underwater Imaging Formation Model-Embedded Multiscale Deep Neural Network for Underwater Image Enhancement

Fucui Li, Difei Lu, ChengLang Lu, Qiuping Jiang
2022 Mathematical Problems in Engineering  
The proposed method has been validated for the UIE task on a real-world underwater image dataset and the experimental results well demonstrate the superiority of our method over the existing ones for UIE  ...  Instead of estimating a global background light magnitude and a transmission matrix separately in traditional image restoration-based UIE methods, we directly generate a single variable as the joint estimation  ...  LR22F020002 and the Fundamental Research Funds for the Provincial Universities of Zhejiang under grant no. SJLZ2020003.  ... 
doi:10.1155/2022/8330985 doaj:9ce45d749eda4565b8669bbec396d6c5 fatcat:m4zstb5sx5an5fnodgsc5t63qu

Benchmarking Underwater Image Enhancement and Restoration, and Beyond

Guojia Hou, Xin Zhao, Zhenkuan Pan, Huan Yang, Lu Tan, Jingming Li
2020 IEEE Access  
In this paper, we first design an underwater image synthesis algorithm (UISA), in which depending on the real-world underwater image, we can produce a synthetic underwater image from an outdoor ground-truth  ...  Based on this strategy, we establish a new large-scale benchmark that contains ground-truth images and synthetic underwater images of the same scene, called synthetic underwater image dataset (SUID).  ...  ACKNOWLEDGMENT (Guojia Hou and Xin Zhao contributed equally to this work.)  ... 
doi:10.1109/access.2020.3006359 fatcat:lrh2l4nsmjdyri7a4dwtianyxu

Deep Learning Approach for Submerged Image Enhancement

Dr. Geeta Hanji
2021 International Journal for Research in Applied Science and Engineering Technology  
Hence for this we first undertook a large scale underwater image dataset which is trained by convolution neural network (CNN) and then we have studied and implemented a deep learning approach called very  ...  Underwater photos frequently upshot in low contrast, blurred, color distortion, hazy, poor visible images.  ...  The system first uses the real time images to train the module, which consist of images of the best quality images of the underwater scenario.Next when the image is uploaded to VDSR model for restoring  ... 
doi:10.22214/ijraset.2021.38391 fatcat:nyrtne4mwff7vmjqxtzegimfsq
« Previous Showing results 1 — 15 out of 715 results