Please use this identifier to cite or link to this item:
Title: DeepCaustics: Classification and Removal of Caustics From Underwater Imagery
Authors: Forbes, Timothy 
Goldsmith, Mark 
Mudur, Sudhir 
Poullis, Charalambos 
Major Field of Science: Engineering and Technology
Field Category: Electrical Engineering - Electronic Engineering - Information Engineering
Issue Date: 21-Jun-2018
Source: IEEE Journal of Oceanic Engineering, 2019, Vol. 44, no. 3, pp. 728 - 738
Volume: 44
Issue: 3
Start page: 728
End page: 738
Project: Advanced VR, iMmersive serious games and Augmented REality as tools to raise awareness and access to European underwater CULTURal heritage 
Journal: IEEE Journal of Oceanic Engineering 
Abstract: Caustics are complex physical phenomena resulting from the projection of light rays being reflected or refracted by a curved surface. In this paper, we address the problem of classifying and removing caustics from images and propose a novel solution based on two convolutional neural networks: SalienceNet and DeepCaustics. Caustics result in changes in illumination that are continuous in nature; therefore, the first network is trained to produce a classification of caustics that is represented as a saliency map of the likelihood of caustics occurring at a pixel. In applications where caustic removal is essential, the second network is trained to generate a caustic-free image. It is extremely hard to generate real ground truth for caustics. We demonstrate how synthetic caustic data can be used for training in such cases, and then transfer the learning to real data. To the best of our knowledge, out of the handful of techniques that have been proposed, this is the first time that the complex problem of caustic removal has been reformulated and addressed as a classification and learning problem. This paper is motivated by the real-world challenges in underwater archaeology.
ISSN: 0364-9059
DOI: 10.1109/JOE.2018.2838939
Rights: Attribution-NonCommercial-NoDerivatives 4.0 International
Type: Article
Affiliation : Concordia University 
Appears in Collections:Άρθρα/Articles

Files in This Item:
File Description SizeFormat
DeepCaustics.pdf2.13 MBAdobe PDFView/Open
CORE Recommender
Show full item record


checked on Oct 16, 2020

Page view(s)

checked on Oct 19, 2020


checked on Oct 19, 2020

Google ScholarTM



This item is licensed under a Creative Commons License Creative Commons