A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
An Underwater Image Enhancement Benchmark Dataset and Beyond
[article]
2019
arXiv
pre-print
In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. ...
Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. ...
CONCLUSION, LIMITATIONS, AND FUTURE WORK In this paper, we have constructed an underwater image enhancement benchmark dataset which offers large-scale real underwater images and the corresponding reference ...
arXiv:1901.05495v2
fatcat:2gwcxf37nbfjzgmxxrcqeqcite
Benchmarking Underwater Image Enhancement and Restoration, and Beyond
2020
IEEE Access
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). ...
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 ...
ACKNOWLEDGMENT (Guojia Hou and Xin Zhao contributed equally to this work.) ...
doi:10.1109/access.2020.3006359
fatcat:lrh2l4nsmjdyri7a4dwtianyxu
Marine Snow Removal Benchmarking Dataset
[article]
2021
arXiv
pre-print
This paper introduces a new benchmarking dataset for marine snow removal of underwater images. ...
We propose two marine snow removal tasks using the dataset and show the first benchmarking results of marine snow removal. The Marine Snow Removal Benchmarking Dataset is publicly available online. ...
Extreme images often have an untypical degradation beyond that of a Gaussian model, and the numbers of available images for training and modifying restoration algorithms are also limited. ...
arXiv:2103.14249v2
fatcat:dnochcr34ra6degyuzzafd6eiy
ENHANCEMENT OF UNDERWATER IMAGES WITH ARTIFICIAL INTELLIGENCE
2024
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Within the scope of the project, An Underwater Image Enhancement Benchmark Dataset and Beyond Dataset and Large Scale Underwater Image Dataset datasets were used. ...
This project aims to use artificial intelligence methods for colour enhancement of underwater images. ...
ACKNOWLEDGEMENTS This study has been supported by The Scientific and Technological Research Council of Turkey (TÜBİTAK) under 2209-B project number: 1139B412200670. ...
doi:10.5194/isprs-archives-xlviii-4-w9-2024-149-2024
fatcat:3povo3imonbaxjm3l7odr4frmq
UIR-Net: A Simple and Effective Baseline for Underwater Image Restoration and Enhancement
2022
Remote Sensing
Because of the unique physical and chemical properties of water, obtaining high-quality underwater images directly is not an easy thing. ...
Hence, recovery and enhancement are indispensable steps in underwater image processing and have therefore become research hotspots. ...
An underwater image enhancement benchmark dataset and beyond with Snow (UIEBD-Snow) To explore the generalization of our work in image enhancement tasks, the same operation that was applied on the MSIRB ...
doi:10.3390/rs15010039
fatcat:kerbkeq7yfhf3mq7xve2573nlq
3D RECONSTRUCTION AND MESH OPTIMIZATION OF UNDERWATER SPACES FOR VIRTUAL REALITY
2020
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
minimize differences among images of the dataset, and image sharpening to strengthen the edges of the scene. ...
In this contribution, we propose a versatile image-based methodology for 3D reconstructing underwater scenes of high fidelity and integrating them into a virtual reality environment. ...
ACKNOWLEDGEMENTS
This research has been co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH ...
doi:10.5194/isprs-archives-xliii-b2-2020-949-2020
fatcat:3elnueu7zjbnxpg5m6evgk3usi
Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detection
[article]
2023
arXiv
pre-print
The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. ...
Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. ...
Our test dataset comprised 26,158 night-sunny images from BDD100K, along with an additional 3,775 images collected from the Foggy Cityscapes [51] and Adverse-Weather [52] datasets. ...
arXiv:2401.05401v1
fatcat:3ufvpltskffonms2fiinwc6hqa
A Dataset with Multibeam Forward-Looking Sonar for Underwater Object Detection
[article]
2022
arXiv
pre-print
To verify the practicality of UATD, we apply the dataset to the state-of-the-art detectors and provide corresponding benchmarks for its accuracy and efficiency. ...
Multibeam forward-looking sonar (MFLS) plays an important role in underwater detection. There are several challenges to the research on underwater object detection with MFLS. ...
We thank the Dalian Key Laboratory of Underwater Robot of Dalian University of Technology for their support during the data collection. ...
arXiv:2212.00352v1
fatcat:kjdkzsdlpre5royzxmod4vibmy
Underwater Image Enhancement Using Wavelet Fusion
2022
International Journal for Research in Applied Science and Engineering Technology
Here we introduce an improved method for underwater image enhancement based on the fusion method that is capable to restore accurately underwater images. ...
Low contrast, color distortion and poor visual appearance are the major issues that an underwater image has to undergo. ...
An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Trans. ...
doi:10.22214/ijraset.2022.47693
fatcat:rfsye5bkubhzlh24wjiximpc7y
A Novel Underwater Image Enhancement and Improved Underwater Biological Detection Pipeline
[article]
2022
arXiv
pre-print
Extensive experiments and comprehensive evaluation on the URPC2021 benchmark dataset demonstrate the effectiveness and adaptivity of our methods. ...
Beyond that, this paper conducts an exhaustive analysis of the role of training data on performance. ...
The images of this benchmark dataset are obtained by frame rate interception of the video captured by the underwater robot ROV in the natural environment. ...
arXiv:2205.10199v1
fatcat:hzcyosbuk5hlpf7bhonvcxleci
Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception
[article]
2020
arXiv
pre-print
By thorough experimental evaluation on the UFO-120 and other standard datasets, we demonstrate that Deep SESR outperforms the existing solutions for underwater image enhancement and super-resolution. ...
In this paper, we introduce and tackle the simultaneous enhancement and super-resolution (SESR) problem for underwater robot vision and provide an efficient solution for near real-time applications. ...
Finally, we acknowledge our colleagues at the IRVLab 3 for their assistance in data collection, annotation, and in preparation of media files. ...
arXiv:2002.01155v1
fatcat:xqurixesvvfj7gpebhkx2x3tgm
UIF: An Objective Quality Assessment for Underwater Image Enhancement
[article]
2022
arXiv
pre-print
To fill this gap, we propose an Underwater Image Fidelity (UIF) metric for objective evaluation of enhanced underwater images. ...
In addition, we have also established a large-scale UIE database with subjective scores, namely Underwater Image Enhancement Database (UIED), which is utilized as a benchmark to compare all objective metrics ...
To fill this void, the UIED dataset is developed as the largest-ever subjective database of UIE images, which can serve as a benchmark to develop and evaluate objective approaches. ...
arXiv:2205.09392v1
fatcat:idexthqf65gnbdvhxl5kv7zvpu
SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots
[article]
2022
arXiv
pre-print
Extensive performance evaluation of SVAM-Net on benchmark datasets clearly demonstrates its effectiveness for underwater SOD. ...
We also validate its generalization performance by several ocean trials' data that include test images of diverse underwater scenes and waterbodies, and also images with unseen natural objects. ...
We collect these images from two major sources: (i) Existing unlabeled datasets: we utilize benchmark datasets that are generally used for underwater image enhancement and superresolution tasks; specifically ...
arXiv:2011.06252v2
fatcat:crctlr7i5jcqbdafbejg5ix7l4
An In-depth Survey of Underwater Image Enhancement and Restoration
2019
IEEE Access
As an important problem in image processing and computer vision, the restoration and enhancement of underwater image are necessary for numerous practical applications. ...
Over the last few decades, underwater image restoration and enhancement have been attracting an increasing amount of research effort. ...
However, an in-depth exploration of underwater restoration and enhancement methods, image quality evaluation techniques and related datasets is still missed. ...
doi:10.1109/access.2019.2932611
fatcat:ixdt4jjjjnc37jbt5lpqcmh33q
Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration
[article]
2022
arXiv
pre-print
More importantly, we have demonstrated a comprehensive validation of enhanced images across various high-level vision tasks, e.g., underwater image semantic segmentation, and diver's 2D pose estimation ...
An extensive set of experiments have been carried out to show the efficacy of the proposed scheme over existing best-published literature on benchmark datasets. ...
EXPERIMENTAL SETUP
Datasets and Training Setup We have utilized the publicly available underwater image enhancement and super-resolution benchmarks, namely UIEB [37] , EUVP [28] , and UFO-120 [26] ...
arXiv:2106.07910v3
fatcat:qm6zjvbkrzbulmrwemqilafsma
« Previous
Showing results 1 — 15 out of 1,069 results