TY - GEN
T1 - Rating realism assessment for computer generated imagery
AU - Huang, Wen Jung
AU - Yeh, Chia Hung
AU - Kuo, Chia Chen
AU - Cheng, Yuan Chen
AU - Lin, Jia Ying
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/25
Y1 - 2017/7/25
N2 - Computer-generated imagery (CGI) is becoming integral to a movie's story and appeal, and even dominates the film's success at box office. Currently the CGI realism is evaluated by post-production supervisors, and few objective realism assessments focus on this area. This paper investigates enhanced feature learning and classifier training for CGI assessment by deep learning. A training-set-selection method is proposed to select proper samples, which is crucial to deep learning training. Then the selected samples are converted into entropy images with enhanced features. We adopt a convolutional neural network for feature learning and classifier training to estimate the realism of CGI. Experimental results show that the developed matric has acceptable accuracy when compared to the grout truth. In addition, the rating result of the proposed assessment is very close to that of human visual perception.
AB - Computer-generated imagery (CGI) is becoming integral to a movie's story and appeal, and even dominates the film's success at box office. Currently the CGI realism is evaluated by post-production supervisors, and few objective realism assessments focus on this area. This paper investigates enhanced feature learning and classifier training for CGI assessment by deep learning. A training-set-selection method is proposed to select proper samples, which is crucial to deep learning training. Then the selected samples are converted into entropy images with enhanced features. We adopt a convolutional neural network for feature learning and classifier training to estimate the realism of CGI. Experimental results show that the developed matric has acceptable accuracy when compared to the grout truth. In addition, the rating result of the proposed assessment is very close to that of human visual perception.
UR - http://www.scopus.com/inward/record.url?scp=85028512083&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85028512083&partnerID=8YFLogxK
U2 - 10.1109/ICCE-China.2017.7991128
DO - 10.1109/ICCE-China.2017.7991128
M3 - Conference contribution
AN - SCOPUS:85028512083
T3 - 2017 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017
SP - 327
EP - 328
BT - 2017 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017
Y2 - 12 June 2017 through 14 June 2017
ER -