Underwater Image Enhancement via Learning Water Type Desensitized Representations
Authors:
Preprint
Abstract
We present a novel underwater image enhancement method termed SCNet to improve the image quality meanwhile cope with the degradation diversity caused by the water. SCNet is based on normalization schemes across both spatial and channel dimensions with the key idea of learning water type desensitized features. Specifically, we apply whitening to de-correlate activations across spatial dimensions for each instance in a mini-batch. We also eliminate channel-wise correlation by standardizing and re-injecting the first two moments of the activations across channels. The normalization schemes of spatial and channel dimensions are performed at each scale of the U-Net to obtain multi-scale representations. With such water type irrelevant encodings, the decoder can easily reconstruct the clean signal and be unaffected by the distortion types. Experimental results on two real-world underwater image datasets show that our approach can successfully enhance images with diverse water types, and achieves competitive performance in visual quality improvement.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space EmbeddingIEEE Transactions on Image Processing, 2021
- An Underwater Image Enhancement Benchmark Dataset and BeyondIEEE Transactions on Image Processing, 2019
- WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater ImagesIEEE Robotics and Automation Letters, 2017
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network2017
- Underwater Image Restoration Based on Image Blurriness and Light AbsorptionIEEE Transactions on Image Processing, 2017
- Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution PriorIEEE Transactions on Image Processing, 2016
- Underwater Image Enhancement by Wavelength Compensation and DehazingIEEE Transactions on Image Processing, 2011