Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/19169
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. | URI: | https://hdl.handle.net/20.500.14279/19169 | ISSN: | 03649059 | DOI: | 10.1109/JOE.2018.2838939 | Rights: | Attribution-NonCommercial-NoDerivatives 4.0 International | Type: | Article | Affiliation : | Concordia University | Publication Type: | Peer Reviewed |
Appears in Collections: | Άρθρα/Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
DeepCaustics.pdf | 2.13 MB | Adobe PDF | View/Open |
CORE Recommender
SCOPUSTM
Citations
8
checked on Nov 6, 2023
WEB OF SCIENCETM
Citations
9
Last Week
0
0
Last month
0
0
checked on Oct 29, 2023
Page view(s) 50
357
Last Week
1
1
Last month
13
13
checked on Aug 28, 2024
Download(s)
246
checked on Aug 28, 2024
Google ScholarTM
Check
Altmetric
This item is licensed under a Creative Commons License