Abstract | ||
---|---|---|
With the development of three-dimensional computer graphics (3DCG) technology, expressing various objects and phenomena graphically became possible. However, there is no method for quantitatively evaluating the realism of the generated CG images. In recent years, deep learning has been widely used for its image discrimination performance beyond that of human beings. We propose a deep learning-based method that enables quantitative evaluation of the realism of CG images with has high image discrimination ability. The results of implementation using convolution neural networks (CNNs) are presented.
|
Year | DOI | Venue |
---|---|---|
2017 | 10.1145/3145690.3145711 | SA '17: SIGGRAPH Asia 2017
Bangkok
Thailand
November, 2017 |
Keywords | Field | DocType |
CG,Realism,Quantitative evaluation,Deep Learning,CNN | Computer vision,Computer graphics (images),Convolution,Computer science,Artificial intelligence,Deep learning,Artificial neural network,Computer graphics,Realism | Conference |
ISBN | Citations | PageRank |
978-1-4503-5405-9 | 0 | 0.34 |
References | Authors | |
2 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Masaaki Sato | 1 | 0 | 0.68 |
Masataka Imura | 2 | 85 | 18.80 |