Deep Color Mismatch Correction In Stereoscopic 3d Images

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 cons...

Full description

Saved in:
Bibliographic Details
Main Authors: Croci, Simone, Ozcinar, Cagri, Zerman, Emin, Dudek, Roman, Knorr, Sebastian, Smolic, Aljosa
Format: Conference Proceeding
Language:English
Subjects:
color correction
Color mismatch
convolutional neural network
Image color analysis
Neural networks
Stereo image processing
stereoscopic 3D
Supervised learning
Three-dimensional displays
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2381-8549
DOI:10.1109/ICIP42928.2021.9506036