Download presentation
Presentation is loading. Please wait.
Published byMarsha Wilcox Modified over 8 years ago
1
A Progressive Tri-level Segmentation Approach for Topology-Change-Aware Video Matting Jinlong Ju 1, Jue Wang 3, Yebin Liu 1, Haoqian Wang 2, Qionghai Dai 1 1.Department of Automation, Tsinghua University, China 2.Graduate School at Shenzhen, Tsinghua University, China 3.Adobe Research, USA
2
The goal Interactive video object segmentation and matting Initial keyframe segmentation Local correction
3
Previous work 3D volume segmentation (global optimization) – Hard to converge Interactive video cutout [Wang et al., SIGGRAPH’05] Video object cut & paste [Li et al., SIGGRAPH’05]
4
Previous work Tracking & segmentation – Easy and intuitive workflow Frame t Frame t+1 Video SnapCut [Bai et al., SIGGRAPH’09] Unbiased Directional Classifiers [Zhong et al., SIGGRAPH Asia’12] Video Object Segmentation by Tracking Regions. ICCV’09. Object Tracking and Segmentation in a Closed Loop. ISVC'10.
5
Previous work Video matting Video Matting of Complex Scenes [Chuang et al., SIGGRAPH’02] Towards Temporally-Coherent Video Matting [Bai et al., Mirage’11]
6
Main ideas Previous methods Our approach Global, one-time optimization Progressive Binary segmentation -> trimap -> matting Tri-level segmentation -> matting
7
Framework Frame-to-frame propagation Frame t Frame t+1
8
Tri-level initial segmentation Step 1: coarse object alignment – SIFT feature tracking and alignment – Optical flow Frame t Frame t-1
9
Initial Tri-level segmentation Step 2: color models Frame t Frame t-1
10
Initial Tri-level segmentation Frame t Frame t-1
11
Initial Tri-level segmentation Comparison Frame t Frame t-1 Our initial labelingColor probability maps of Gaussian Mixtures
12
Initial Tri-level segmentation Frame tFrame t+1 Unmatched pixels
13
Initial Tri-level segmentation Step 5: local smoothing – Mean shift, same color models for each MS region Frame tFrame t+1 Initial map
14
Tri-level segmentation Refinement Goal: remove large unknown regions Before refinementAfter refinement
15
Tri-level segmentation Refinement Cross-frame window matching + shape prior Frame tFrame t+1
16
Tri-level segmentation Refinement Cross-frame window matching + shape prior Frame tFrame t+1
17
Final matting Directly use tri-level segmentation as trimap (ideally) After mattingBefore matting
18
Results Tri-level segmentation Final result Adobe After Effects RotoBrush
19
Results Tri-level segmentation Final result Adobe After Effects RotoBrush
20
Quantitative comparison
21
Conclusion Tri-label labeling Progressive segmentation Handles topology-change, fast-moving objects well Limitations: – Segmentation is a little bit too aggressive (not ideal for matting) – A few thresholds to tune
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.