Title :
GPU based video stylization
Author :
Zhao, Yang ; Xie, Deng-en ; Xu, Dan
Author_Institution :
Dept. of Comput. Sci., Yunnan Univ., Kunming
Abstract :
In this paper, we present a GPU based video stylization framework that can artistically stylize video stream in real time. In this framework, firstly, we use a separable implementation of bilateral filter as an adaptive and iterative smoothing operation that selectively simplifies image color, leading to an abstracted look. Secondly, we perform a soft color quantization step on the abstracted video. A significant advantage of the soft color quantization implementation is preserving temporal coherence and reducing computation time as well. Successively, some optional approaches are designed to generate different artistic styles. We evaluate the effectiveness of our stylization framework with the experiment results.
Keywords :
image colour analysis; iterative methods; smoothing methods; video streaming; GPU; adaptive smoothing operation; bilateral filter; image color; iterative smoothing operation; soft color quantization step; temporal coherence; video stream; video stylization; Animation; Cybernetics; Graphics; Image segmentation; Machine learning; Quantization; Real time systems; Rendering (computer graphics); Streaming media; Videoconference; GPU; NPR; Video stylization;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4620899
