TY - JOUR
T1 - Block-based depth maps interpolation for efficient multiview content generation
AU - Wang, Hung Ming
AU - Huang, Chun Hao
AU - Yang, Jar Ferr
N1 - Funding Information:
Manuscript received November 9, 2010; revised February 22, 2011 and April 2, 2011; accepted April 10, 2011. Date of publication April 29, 2011; date of current version December 7, 2011. This work was supported in part by the National Science Council of Taiwan, under Grant NSC 100-2218-E-006-017. This paper was recommended by Associate Editor L. Onural.
PY - 2011/12
Y1 - 2011/12
N2 - For multiview video generation from 2-D video sequences, the most important stage is to efficiently synthesize the corresponding depth maps for all video frames. The depth map generation involving precise object segmentation and depth assignment requires intensive computation and human assistance which could be costly and possibly inconsistent. To achieve reliable depth map generation, an efficient depth map interpolation method from the existing pairs of keyframes and their corresponding depth maps at the both ends of video scene is presented. The proposed method contains forward/backward motion alignment, block-based updating, object-based updating, frame selection mechanism, and depth adjustment. Experimental results show that the proposed method can generate the depth maps successfully after objective and subjective evaluations. We believe that it could greatly help to achieve multiview video generation from 2-D video sequences effectively.
AB - For multiview video generation from 2-D video sequences, the most important stage is to efficiently synthesize the corresponding depth maps for all video frames. The depth map generation involving precise object segmentation and depth assignment requires intensive computation and human assistance which could be costly and possibly inconsistent. To achieve reliable depth map generation, an efficient depth map interpolation method from the existing pairs of keyframes and their corresponding depth maps at the both ends of video scene is presented. The proposed method contains forward/backward motion alignment, block-based updating, object-based updating, frame selection mechanism, and depth adjustment. Experimental results show that the proposed method can generate the depth maps successfully after objective and subjective evaluations. We believe that it could greatly help to achieve multiview video generation from 2-D video sequences effectively.
UR - http://www.scopus.com/inward/record.url?scp=83255184446&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=83255184446&partnerID=8YFLogxK
U2 - 10.1109/TCSVT.2011.2148510
DO - 10.1109/TCSVT.2011.2148510
M3 - Article
AN - SCOPUS:83255184446
SN - 1051-8215
VL - 21
SP - 1847
EP - 1858
JO - IEEE Transactions on Circuits and Systems for Video Technology
JF - IEEE Transactions on Circuits and Systems for Video Technology
IS - 12
M1 - 5756653
ER -