STEREOSCOPIC DATASET FROM A VIDEO GAME: DETECTING CONVERGED AXES AND PERSPECTIVE DISTORTIONS IN S3D VIDEOS

被引：0
作者：
Malyshev, Kirill [1 ]
Lavrushkin, Sergey [1 ]
Vatolin, Dmitriy [1 ]
机构：
[1] Lomonosov Moscow State Univ, Moscow, Russia
来源：
2020 INTERNATIONAL CONFERENCE ON 3D IMMERSION (IC3D) | 2020年
基金：
俄罗斯基础研究基金会;
关键词：
Perspective distortion; converged axes; geometric distortions; stereoscopic video; deep learning;
D O I：
10.1109/IC3D51119.2020.9376375
中图分类号：
TB8 [摄影技术];
学科分类号：
0804 ;
摘要：
This paper presents a method for generating stereoscopic or multi-angle video frames using a computer game (Grand Theft Auto V). We developed a mod that captures synthetic frames allows us to create geometric distortions like those that occur in a real video. These distortions are the main cause of viewer discomfort when watching 3D movies. Datasets generated in this way can aid in solving problems related to machine-learning-based assessment of stereoscopic- or multi-angle-video quality. We trained a convolutional neural network to evaluate perspective distortions and converged camera axes in stereoscopic video, then tested it on real 3D movies. The neural network discovered multiple examples of these distortions.
引用
收藏
页数：7
相关论文
共 23 条
[1]  
Antsiferova A., 2017, INT C 3D IMM, P1
[2]   A Naturalistic Open Source Movie for Optical Flow Evaluation [J].
Butler, Daniel J. ;
Wulff, Jonas ;
Stanley, Garrett B. ;
Black, Michael J. .
COMPUTER VISION - ECCV 2012, PT VI, 2012, 7577 :611-625
[3]  
Geiger A, 2012, PROC CVPR IEEE, P3354, DOI 10.1109/CVPR.2012.6248074
[4]  
Georgiev M, 2013, IEEE IMAGE PROC, P24, DOI 10.1109/ICIP.2013.6738006
[5]  
Hurl B, 2019, IEEE INT VEH SYM, P2522, DOI 10.1109/IVS.2019.8813809
[6]  
Johnson-Roberson Matthew, 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA), P746, DOI 10.1109/ICRA.2017.7989092
[7]   Accelerating garbage collection for 3D MLC flash memory with SLC blocks [J].
Li, Shuai ;
Tong, Wei ;
Liu, Jingning ;
Wu, Bing ;
Feng, Yazhi .
2019 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD), 2019,
[8]   Learning a convolutional neural network for propagation-based stereo image segmentation [J].
Li, Xujie ;
Huang, Hui ;
Zhao, Hanli ;
Wang, Yandan ;
Hu, Mingxiao .
VISUAL COMPUTER, 2020, 36 (01) :39-52
[9]  
McNulty O., 2017, THESIS U SYDNEY SYDN
[10]  
Menze M, 2015, PROC CVPR IEEE, P3061, DOI 10.1109/CVPR.2015.7298925
123