Title :
Video Synthesis From Still Images Using 3-D Flow Models
Author :
Zhao, Yutao ; Liu, Yuncai
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiaotong Univ., Shanghai
fDate :
6/30/1905 12:00:00 AM
Abstract :
In this letter, we present a new approach to synthesize video from still images. The method first models 3-D flows, and then it proposes image modulation. Finally, the 3-D flow models are projected onto image planes to produce the final video. We use some results of computational flow dynamics to model the flows and propose image matting and inpainting methods that are more appropriate to our animation. Our algorithm can effectively handle still images that have flows. Experiments demonstrate that our synthesis method can produce good-looking videos.
Keywords :
computer animation; image sequences; video signal processing; 3-D flow models; animation; computational flow dynamics; image inpainting methods; image matting methods; image modulation; image sequences; still images; video synthesis; Animation; Character generation; Computational modeling; Computer graphics; Computer simulation; Costs; Frequency; Image analysis; Image processing; Image resolution; 3-D flow models; Computational flow dynamics; image matting and inpainting; still images; video synthesis;
Journal_Title :
Signal Processing Letters, IEEE
DOI :
10.1109/LSP.2008.925753