Smart Scribbles for Image Mating
Xin Yang, Yu Qiao, Shaozhe Chen, Shengfeng He, Baocai Yin, Qiang, Zhang, Xiaopeng Wei, Rynson W.H.Lau

TL;DR
This paper introduces 'smart scribbles', an interactive image matting framework that efficiently guides users to draw minimal scribbles, resulting in high-quality alpha mattes with less effort and artifacts, outperforming existing methods.
Contribution
The paper proposes a novel interactive framework that intelligently guides minimal user input for high-quality image matting without large datasets, balancing effort and accuracy.
Findings
Produces more accurate alpha mattes than state-of-the-art methods.
Requires less user effort with fewer scribbles.
Operates effectively without large-scale training datasets.
Abstract
Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles. Drawing a fne trimap requires a large amount of user effort, while using scribbles can hardly obtain satisfactory alpha mattes for non-professional users. Some recent deep learning-based matting networks rely on large-scale composite datasets for training to improve performance, resulting in the occasional appearance of obvious artifacts when processing natural images. In this article, we explore the intrinsic relationship between user input and alpha mattes and strike a balance between user effort and the quality of alpha mattes. In particular, we propose an interactive framework, referred to as smart scribbles, to guide users to draw few scribbles on the input images to produce high-quality alpha mattes. It frst infers the most informative regions of an image for drawing…
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.
