Rating realism assessment for computer generated imagery

Wen Jung Huang, Chia Hung Yeh, Chia Chen Kuo, Yuan Chen Cheng, Jia Ying Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages327-328
Number of pages2
ISBN (Electronic)9781509040179
DOIs
Publication statusPublished - 2017 Jul 25
Event4th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017 - Taipei, United States
Duration: 2017 Jun 122017 Jun 14

Publication series

Name2017 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017

Other

Other4th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2017
Country/TerritoryUnited States
CityTaipei
Period2017/06/122017/06/14

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications
  • Signal Processing
  • Biomedical Engineering
  • Instrumentation
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Rating realism assessment for computer generated imagery'. Together they form a unique fingerprint.

Cite this