TY - GEN
T1 - CTDP Depacking with Guided Depth Upsampling Networks for Realization of Multiview 3D Video
AU - Yang, Wei Jong
AU - Chen, Bo Xun
AU - Yang, Jar Ferr
N1 - Funding Information:
Acknowledgments. This work was partially supported by the Ministry of Science and Technology, Taiwan, under Grant MOST 111-2221-E-080 and Qualcomm, USA under Grant SOW#NAT-435536.
Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2023
Y1 - 2023
N2 - With the advancement of 3D display technology, the original 3D stereo-view systems requiring 3D glasses have evolved to multiple-view naked-eyes 3D displays. For 2D broadcasting systems, we can pack one view and its corresponding depth map into a frame in the transmission side and generate multiple views by the depth image-based rendering (DIBR) engine at the receivers. Up to now, the centralized texture depth packing (CTDP) frame-compatible format is the best solution for view and depth packing. In this paper, we propose an improved CTDP depacking method and realize it with DIBR process to achieve real-time 3D multiview exhibition. To maintain the quality of the depacked depth map, in the CTDP depacking process, we suggest a deep learning-based guided depth upsampling network. The experimental results demonstrate that the proposed 3D multiview system can successfully depack CTDP video and generate 9-view 3D movies in real-time. The proposed guided depth upsampling network achieves a better quality of the generated views than the traditional algorithms.
AB - With the advancement of 3D display technology, the original 3D stereo-view systems requiring 3D glasses have evolved to multiple-view naked-eyes 3D displays. For 2D broadcasting systems, we can pack one view and its corresponding depth map into a frame in the transmission side and generate multiple views by the depth image-based rendering (DIBR) engine at the receivers. Up to now, the centralized texture depth packing (CTDP) frame-compatible format is the best solution for view and depth packing. In this paper, we propose an improved CTDP depacking method and realize it with DIBR process to achieve real-time 3D multiview exhibition. To maintain the quality of the depacked depth map, in the CTDP depacking process, we suggest a deep learning-based guided depth upsampling network. The experimental results demonstrate that the proposed 3D multiview system can successfully depack CTDP video and generate 9-view 3D movies in real-time. The proposed guided depth upsampling network achieves a better quality of the generated views than the traditional algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85149905164&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149905164&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-28076-4_13
DO - 10.1007/978-3-031-28076-4_13
M3 - Conference contribution
AN - SCOPUS:85149905164
SN - 9783031280757
T3 - Lecture Notes in Networks and Systems
SP - 136
EP - 152
BT - Advances in Information and Communication - Proceedings of the 2023 Future of Information and Communication Conference, FICC 2023
A2 - Arai, Kohei
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th Future of Information and Computing Conference, FICC 2023
Y2 - 2 March 2023 through 3 March 2023
ER -