Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception

02/04/2020
by   Md Jahidul Islam, et al.
18

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. We present Deep SESR, a residual-in-residual network-based generative model that can learn to restore perceptual image qualities at 2x, 3x, or 4x higher spatial resolution. We supervise its training by formulating a multi-modal objective function that addresses the chrominance-specific underwater color degradation, lack of image sharpness, and loss in high-level feature representation. It is also supervised to learn salient foreground regions in the image, which in turn guides the network to learn global contrast enhancement. We design an end-to-end training pipeline to jointly learn the saliency prediction and SESR on a shared hierarchical feature space for fast inference. Moreover, we present UFO-120, the first dataset to facilitate large-scale SESR learning; it contains over 1500 training samples and a benchmark test set of 120 samples. 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. We also validate its generalization performance on several test cases that include underwater images with diverse spectral and spatial degradation levels, and also terrestrial images with unseen natural objects. Lastly, we analyze its computational feasibility for single-board deployments and demonstrate its operational benefits for visually-guided underwater robots. The model and dataset information will be available at: https://github.com/xahidbuffon/Deep-SESR.

READ FULL TEXT

page 1

page 3

page 5

page 7

page 8

page 9

page 10

research
09/20/2019

Underwater Image Super-Resolution using Deep Residual Multipliers

We present a deep residual network-based generative model for single ima...
research
03/23/2019

Fast Underwater Image Enhancement for Improved Visual Perception

In this paper, we present a conditional generative adversarial network-b...
research
11/12/2020

SVAM: Saliency-guided Visual Attention Modeling by Autonomous Underwater Robots

This paper presents a holistic approach to saliency-guided visual attent...
research
04/02/2020

Semantic Segmentation of Underwater Imagery: Dataset and Benchmark

In this paper, we present the first large-scale dataset for semantic Seg...
research
01/08/2022

SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perception

Due to the wavelength-dependent light attenuation, refraction and scatte...
research
07/15/2021

Deep Automatic Natural Image Matting

Automatic image matting (AIM) refers to estimating the soft foreground f...
research
12/10/2020

A Generative Approach for Detection-driven Underwater Image Enhancement

In this paper, we introduce a generative model for image enhancement spe...

Please sign up or login with your details

Forgot password? Click here to reset