Visual realism is defined as the degree an image appears to people to be a photo rather than computer generated. Predicting image visual realism is a challenging yet important task for the visualization and CG communities. For instance, image realism could be used as a metric for CG image quality evaluation or during manipulation of the realism level of computer games. Image realism could also be integrated into content-based image retrieval and image forensics.
Our research explores both image and cognitive factors that influence human perception of image visual realism through a series of psychophysics experiments. Based on such understanding of human perception of image visual realism, we are able to model visual realism both empirically and computationally. Our goal is to build a visual realism predictor that is consistent with human perception, as a first step to enable computers to perceive like humans do.
S. Fan, T. -T. Ng, B. Koenig, J. Herberg, M. Jiang, Z. Shen, Q. Zhao. “Image Visual Realism: From Human Perception to Machine Computation”, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 40.9(2018).
[pdf]
[supplementary material]
[code]
[dataset]
Y. Zhu, Subramanian, R., T.-T. Ng, Winkler, S. and Ratnam, R. "Comparison of human and machine performance for copy-move image forgery detection involving similar but genuine objects." Region 10 Conference (TENCON), 2016 IEEE. IEEE, 2016. [pdf]
B. Wen, Y. Zhu, Subramanian, R., T.-T. Ng, Shen, X. and Winkler, S., 2016, September. COVERAGE—A novel database for copy-move forgery detection. In Image Processing (ICIP), 2016 IEEE International Conference on (pp. 161-165). IEEE. [pdf]
Y. Zhu, T.-T. Ng, Shen, X., & B. Wen, Revisiting copy-move forgery detection by considering realistic image with similar but genuine objects. arXiv preprint arXiv:1601.07262. 2016 [pdf]
S. Fan, T.-T. Ng, J. Herbert, B. Koenig, C. Tan, R. Wang, “An Automated Estimator of Image Visual Realism Based on Human Cognition”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2014. [pdf(19M)] [downsized pdf(400K)] [supplementary material] [video] [poster]
S. Fan, T.-T. Ng, J. Herbert, B. Koenig, C. Tan, K. Leman, “A Benchmark Dataset for Image Visual Realism”, Technical Report, Institute for Infocomm Research, 2014. [pdf]
S. Fan, T.-T. Ng, J. Herbert, B. Koenig, C. Tan, R. Wang, “An Automated Estimator of Image Visual Realism Based on Human Cognition”, Extended Abstract, Vision Meets Cognition workshop, in conjunction with CVPR 2014. (Invited) [pdf]
S. Fan, T.-T. Ng, J. Herbert, B. Koenig, C. Tan, R. Wang, “Human Perception of Visual Realism for Photo and Computer-generated Face Images", ACM Transaction on Applied Perception (TAP), 11.2 (2014): 7. [pdf(12M)] [downsized pdf(300K)] [poster]
T.-T. Ng, and Shih-Fu Chang. "Discrimination of computer synthesized or recaptured images from real images." Digital image forensics. Springer New York, 2013. 275-309. [pdf]
S. Fan, T.-T. Ng, J. Herbert, B. Koenig, X. Shi, “Real or Fake? Human judgments about photographs and computer-generated images of faces”, Technical Brief, ACM Siggraph Asia, Nov 2012. [pdf] [video]
T.-T. Ng, Shih-Fu Chang and Mao-Pei Tsui. "Lessons learned from online classification of photo-realistic computer graphics and photographs." Signal Processing Applications for Public Security and Forensics, 2007. SAFE'07. IEEE Workshop on. IEEE, 2007. [pdf]
T.-T. Ng, Shih-Fu Chang., Lin, C. Y., & Sun, Q. (2006). Passive-blind image forensics. Multimedia Security Technologies for Digital Rights, 15, 383-412. 2006 [pdf]
T.-T. Ng, Shih-Fu Chang, Hsu, J., Xie, L., & Tsui, M. P. Physics-motivated features for distinguishing photographic images and computer graphics. In Proceedings of the 13th annual ACM international conference on Multimedia (pp. 239-248). ACM. 2005. [pdf]