Real-time feature-aware video abstraction

Authors:
Hanli Zhao;Xiaogang Jin;Jianbing Shen;Xiaoyang Mao;Jieqing Feng
Affiliations:
Zhejiang University, State Key Lab of CAD & CG, 310027, Hangzhou, P.R. China;Zhejiang University, State Key Lab of CAD & CG, 310027, Hangzhou, P.R. China;Indiana University-Purdue University, 310027, Indianapolis, USA;University of Yamanashi, 310027, Yamanashi, Japan;Zhejiang University, State Key Lab of CAD & CG, 310027, Hangzhou, P.R. China
Venue:
The Visual Computer: International Journal of Computer Graphics
Year:
2008

Citing 0
Cited 5

AtelierM++: a fast and accurate marbling system

Multimedia Tools and Applications
Fast Shape-Simplifying Image Abstraction Using Graphics Hardware

Edutainment '09 Proceedings of the 4th International Conference on E-Learning and Games: Learning by Playing. Game-based Education System Design and Development
Real-time implementation for weighted-least-squares-based edge-preserving decomposition and its applications

Transactions on edutainment VI
Real-time directional stylization of images and videos

Multimedia Tools and Applications
Real-time image marbleization

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel feature-aware rendering system that automatically abstracts videos and images with the goal of improving the effectiveness of imagery for visual communication tasks. We integrate the bilateral grid to simplify regions of low contrast, which is faster than the separable approximation to the bilateral filter, and use a feature flow-guided anisotropic edge detection filter to enhance regions of high contrast. The edges detected in this paper are smoother, more coherent and stylistic than those of the isotropic difference-of-Gaussian filter. The presented algorithms are highly parallel, allowing a real-time performance on modern GPUs. The implementation of our approach is straightforward. Several experimental examples are given at the end of the paper to demonstrate the effectiveness of our approach.