Painterly rendering with curved brush strokes of multiple sizes
Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image and video based painterly animation
Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering
ACM SIGGRAPH 2004 Papers
Learning Layered Motion Segmentations of Video
International Journal of Computer Vision
From image parsing to painterly rendering
ACM Transactions on Graphics (TOG)
Painterly animation using video semantics and feature correspondence
NPAR '10 Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering
Layered Graph Matching with Composite Cluster Sampling
IEEE Transactions on Pattern Analysis and Machine Intelligence
SIFT Flow: Dense Correspondence across Scenes and Its Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence
Representing and recognizing objects with massive local image patches
Pattern Recognition
| Hi-index | 0.00 |
This paper investigates a novel approach to reduce artifacts and visual flickering in generating painterly animations from real video clips. In the traditional painterly animation methods, the brush strokes are propagated over video frames by calculating optical flows, and the visual impression of animations are severely affected by incorrect correspondences. In our method, we combine motion segmentation and occlusion handing to establish accurate dense feature correspondences, which is shown to robust propagate brush strokes against complex motions and occlusions. Moreover, a beforehand rendering strategy is presented to alleviate stroke flickering. In the experiments, we generate a number of animations in cartoon and oil painting style. The quantitative evaluations of brush stabilization is presented as well.