2018 IEEE International Conference on Image Processing (ICIP)

Visit the conference page.


The image processing community has witnessed remarkable advances in enhancing and restoring images. Nevertheless, restoring the visual quality of underwater images remains a great challenge. End-to-end frameworks might fail to enhance the visual quality of underwater images since in several scenarios it is not feasible to provide the ground truth of the scene radiance. In this work, we propose a CNN-based approach that does not require ground truth data since it uses a set of image quality metrics to guide the restoration learning process. The experiments showed that our method improved the visual quality of underwater images preserving their edges and also performed well considering the UCIQE metric.

Keywords: Underwater Vision, Image Restoration, Image Quality Metrics, Deep Learning

Coming Soon.

Offical Publication

Coming Soon.

Methodology and Results.



author = {W. V. Barbosa and H. G. B. Amaral and T. L. Rocha and E. R. Nascimento},
booktitle = {IEEE International Conference on Image Processing (ICIP)},
title = {Visual-quality-driven learning for underwater vision enhancement},
year = {2018},
month = {Out.},
address = {Athens, GRE},
doi = {10.1109/ICIP.2018.8451356}


We compare this proposed methodology against the following methods:

Coming Soon.


We conducted the experimental evaluation using the datasets:

Coming Soon.


Walysson Vital Barbosa

MSc Student

Henrique Grandinetti Barbosa Amaral

Undergraduate Student

Thiago Lages Rocha

Undergraduate Student

Back to the project page.