Please use this identifier to cite or link to this item:
Title: Deep color mismatch correction in stereoscopic 3D images
Authors: Croci, Simone
Ozcinar, Cagri
Zerman, Emin
Dudek, Roman 
Knorr, Sebastian
Smolic, Aljosa
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
Keywords: Color Correction
Color Mismatch
Convolutional Neural Network
Stereoscopic 3D
Issue Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE) 
Journal: Proceedings - International Conference on Image Processing 
Conference: IEEE International Conference on Image Processing (ICIP 2021) 
Abstract: Color mismatch in stereoscopic 3D (S3D) images can create visual discomfort and affect the performance of S3D image processing algorithms, e.g., for depth estimation. In this paper, we propose a new deep learning-based solution for the problem of color mismatch correction. The proposed solution consists of a multi-task convolutional neural network, where color correction is the primary task and correspondence estimation is the secondary task. For the training and evaluation of the proposed network, a new S3D image dataset with color mismatch was created. Based on this dataset, experiments were conducted showing the effectiveness of our solution.
ISBN: 978-1-6654-4115-5
ISSN: 1522-4880
DOI: 10.1109/ICIP42928.2021.9506036
Source: Proceedings - International Conference on Image Processing, ICIP [ISSN 1522-4880], v. 2021-September, p. 1749-1753, (Enero 2021)
Appears in Collections:Actas de congresos
Show full item record

Page view(s)

checked on Jan 13, 2024

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.