A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
A Lightweight Multi-Branch Context Network for Unsupervised Underwater Image Restoration
Underwater images commonly experience degradation caused by light absorption and scattering in water. Developing lightweight and efficient neural networks to restore degraded images is challenging because of the difficulty in obtaining high-quality paired images and the delicate trade-off between model performance and computational demands. To provide a lightweight and efficient solution for restoring images in terms of color, structure, texture details, etc., enabling the underwater image restoration task to be applied in real-world scenes, we propose an unsupervised lightweight multi-branch context network. Specifically, we design two lightweight multi-branch context subnetworks that enable multiple receptive field feature extraction and long-range dependency modeling to estimate scene radiance and transmission maps. Gaussian blur is adopted to approximate the global background light on the twice-downsampled degraded image. We design a comprehensive loss function that incorporates multiple components, including self-supervised consistency loss and reconstruction loss, to train the network using degraded images in an unsupervised learning manner. Experiments on several underwater image datasets demonstrate that our approach realizes good performance with very few model parameters (0.12 M), and is even comparable to state-of-the-art methods (up to 149 M) in color correction and contrast restoration.
A Lightweight Multi-Branch Context Network for Unsupervised Underwater Image Restoration
Underwater images commonly experience degradation caused by light absorption and scattering in water. Developing lightweight and efficient neural networks to restore degraded images is challenging because of the difficulty in obtaining high-quality paired images and the delicate trade-off between model performance and computational demands. To provide a lightweight and efficient solution for restoring images in terms of color, structure, texture details, etc., enabling the underwater image restoration task to be applied in real-world scenes, we propose an unsupervised lightweight multi-branch context network. Specifically, we design two lightweight multi-branch context subnetworks that enable multiple receptive field feature extraction and long-range dependency modeling to estimate scene radiance and transmission maps. Gaussian blur is adopted to approximate the global background light on the twice-downsampled degraded image. We design a comprehensive loss function that incorporates multiple components, including self-supervised consistency loss and reconstruction loss, to train the network using degraded images in an unsupervised learning manner. Experiments on several underwater image datasets demonstrate that our approach realizes good performance with very few model parameters (0.12 M), and is even comparable to state-of-the-art methods (up to 149 M) in color correction and contrast restoration.
A Lightweight Multi-Branch Context Network for Unsupervised Underwater Image Restoration
Rong Wang (author) / Yonghui Zhang (author) / Yulu Zhang (author)
2024
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
INSTALLATION OF LIGHTWEIGHT UNDERWATER ACOUSTIC ARRAYS
| British Library Online Contents | 2006
Lightweight material aids in facade restoration
Online Contents | 1996
Stilling pool bottom plate underwater restoration device and restoration method
| European Patent Office | 2020
Underwater Fatigue Performance of Structural Lightweight Concrete
| British Library Conference Proceedings | 1994