Foreground segmentation based on multi-resolution and matting
Xintong Yu, Xiaohan Liu, Yisong Chen

TL;DR
This paper introduces a multi-resolution and matting-based foreground segmentation method that improves accuracy by combining adaptive segmentation at various scales with boundary refinement through closed-form matting.
Contribution
The proposed algorithm uniquely integrates multi-resolution segmentation with matting and adaptive selection, enhancing segmentation accuracy in cluttered scenes.
Findings
Effective in cluttered backgrounds
Handles loose initial bounding boxes
Refines boundaries with closed-form matting
Abstract
We propose a foreground segmentation algorithm that does foreground extraction under different scales and refines the result by matting. First, the input image is filtered and resampled to 5 different resolutions. Then each of them is segmented by adaptive figure-ground classification and the best segmentation is automatically selected by an evaluation score that maximizes the difference between foreground and background. This segmentation is upsampled to the original size, and a corresponding trimap is built. Closed-form matting is employed to label the boundary region, and the result is refined by a final figure-ground classification. Experiments show the success of our method in treating challenging images with cluttered background and adapting to loose initial bounding-box.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Enhancement Techniques · Video Surveillance and Tracking Methods · Advanced Vision and Imaging
