GPU based video stylization

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.