U-shape Transformer for Underwater Image Enhancement

The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Be...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on image processing Ročník 32; s. 1
Hlavní autori: Peng, Lintao, Zhu, Chunli, Bian, Liheng
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Attenuation
Channels
Color
Datasets
Electromagnetic absorption
Image enhancement
Image quality
Image segmentation
Modules
Multi-color space loss function
Semantic segmentation
Transformer
Underwater construction
Underwater image dataset
Underwater image enhancement
ISSN:1057-7149, 1941-0042, 1941-0042
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The light absorption and scattering of underwater impurities lead to poor underwater imaging quality. The existing data-driven based underwater image enhancement (UIE) techniques suffer from the lack of a large-scale dataset containing various underwater scenes and high-fidelity reference images. Besides, the inconsistent attenuation in different color channels and space areas is not fully considered for boosted enhancement. In this work, we built a large scale underwater image (LSUI) dataset, which covers more abundant underwater scenes and better visual quality reference images than existing underwater datasets. The dataset contains 4279 real-world underwater image groups, in which each raw image's clear reference images, semantic segmentation map and medium transmission map are paired correspondingly. We also reported an U-shape Transformer network where the transformer model is for the first time introduced to the UIE task. The U-shape Transformer is integrated with a channel-wise multi-scale feature fusion transformer (CMSFFT) module and a spatial-wise global feature modeling transformer (SGFMT) module specially designed for UIE task, which reinforce the network's attention to the color channels and space areas with more serious attenuation. Meanwhile, in order to further improve the contrast and saturation, a novel loss function combining RGB, LAB and LCH color spaces is designed following the human vision principle. The extensive experiments on available datasets validate the state-of-the-art performance of the reported technique with more than 2dB superiority. The dataset and demo code are available on https://bianlab.github.io/.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1057-7149
1941-0042
1941-0042
DOI:10.1109/TIP.2023.3276332