Abstract | ||
---|---|---|
Observing that a motion signal is decomposable into multiple levels, a video generation model which realizes this hypothesis is proposed. The model decomposes motion into a two-level signal involving a global path and local pattern. They are modeled via a latent path in the form of a composite Bezier spline along with a latent sine function respectively. In the application context, the model fills the research gap in its ability to connect an arbitrary number of input key frames smoothly. Experimental results indicate that the model improves in terms of the smoothness of the generated video. In addition, the ability of the model in separating global and local signal has been validated. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-22514-8_16 | ADVANCES IN COMPUTER GRAPHICS, CGI 2019 |
Keywords | Field | DocType |
Global motion path,Local motion pattern,Video generation with key frames,Latent path,Periodic latent function | Spline (mathematics),Computer vision,Computer science,Sine,Bézier curve,Artificial intelligence,Application Context,Smoothness | Conference |
Volume | ISSN | Citations |
11542 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zackary P. T. Sin | 1 | 0 | 2.03 |
Peter H. Ng | 2 | 18 | 4.14 |
Simon Chi Keung Shiu | 3 | 667 | 35.42 |
Fu-lai Chung | 4 | 244 | 34.50 |
Hong Va Leong | 5 | 1099 | 173.04 |