Multi‐scale Information Assembly for Image Matting

Image matting is a long‐standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different‐level information, including the central bodies, large‐grained boundaries, re...

Full description

Saved in:
Bibliographic Details
Published inComputer graphics forum Vol. 39; no. 7; pp. 565 - 574
Main Authors Qiao, Yu, Liu, Yuhao, Zhu, Qiang, Yang, Xin, Wang, Yuxin, Zhang, Qiang, Wei, Xiaopeng
Format Journal Article
LanguageEnglish
Published Oxford Blackwell Publishing Ltd 01.10.2020
Subjects
Assembly
CCS Concepts
Color imagery
Computer graphics
Computing methodologies $Ar Image segmentation
Feature extraction
Image quality
Image representations
Mattes
Semantics
Online AccessGet full text
ISSN0167-7055
1467-8659
DOI10.1111/cgf.14168

Cover

More Information
Summary:Image matting is a long‐standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different‐level information, including the central bodies, large‐grained boundaries, refined details, etc. Based on this observation, in this paper, we propose a multi‐scale information assembly framework (MSIA‐matte) to pull out high‐quality alpha mattes from single RGB images. Technically speaking, given an input image, we extract advanced semantics as our subject content and retain initial CNN features to encode different‐level foreground expression, then combine them by our well‐designed information assembly strategy. Extensive experiments can prove the effectiveness of the proposed MSIA‐matte, and we can achieve state‐of‐the‐art performance compared to most existing matting networks.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0167-7055
1467-8659
DOI:10.1111/cgf.14168