Multi-scale Information Assembly for Image Matting

被引:10
|
作者
Qiao, Yu [1 ]
Liu, Yuhao [1 ]
Zhu, Qiang [1 ]
Yang, Xin [1 ]
Wang, Yuxin [1 ]
Zhang, Qiang [1 ]
Wei, Xiaopeng [1 ]
机构
[1] Dalian Univ Technol, Coll Comp Sci, Dalian, Peoples R China
基金
中国国家自然科学基金;
关键词
CCS Concepts; Image representations; • Computing methodologies $Ar Image segmentation;
D O I
10.1111/cgf.14168
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
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.
引用
收藏
页码:565 / 574
页数:10
相关论文
共 50 条
  • [41] Single Image Super-Resolution via Multi-Scale Information Polymerization Network
    Lu, Tao
    Wang, Yu
    Wang, Jiaming
    Liu, Wei
    Zhang, Yanduo
    IEEE SIGNAL PROCESSING LETTERS, 2021, 28 : 1305 - 1309
  • [42] A Robust Solution to Multi-modal Image Registration by Combining Mutual Information with Multi-scale Derivatives
    Legg, Philip A.
    Rosin, Paul L.
    Marshall, David
    Morgan, James E.
    MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION - MICCAI 2009, PT I, PROCEEDINGS, 2009, 5761 : 616 - +
  • [43] Multi-scale morphological simplification for image segmentation
    Lu, GM
    Yang, Z
    2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 484 - 487
  • [44] Multi-scale image segmentation based on morphology
    Wang, XP
    Hao, CY
    Fan, YY
    Xi, YL
    CHINESE JOURNAL OF ELECTRONICS, 2005, 14 (01): : 119 - 121
  • [45] Image categorization based on multi-scale vocabulary
    Yang, Xin
    Tang, Jinhui
    Wu, Xiuqing
    MIPPR 2007: PATTERN RECOGNITION AND COMPUTER VISION, 2007, 6788
  • [46] CONTEXTUAL MULTI-SCALE IMAGE CLASSIFICATION ON QUADTREE
    Hedhli, Ihsen
    Moser, Gabriele
    Serpico, Sebastiano B.
    Zerubia, Josiane
    2016 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2016, : 1349 - 1353
  • [47] Image steganalysis with multi-scale residual network
    Hao Chen
    Qi Han
    Qiong Li
    Xiaojun Tong
    Multimedia Tools and Applications, 2023, 82 : 22009 - 22031
  • [48] Single Image Dehazing by Multi-Scale Fusion
    Ancuti, Codruta Orniana
    Ancuti, Cosmin
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (08) : 3271 - 3282
  • [49] Multi-Scale Attention Network for Image Cropping
    Lian, Tianpei
    Xian, Ke
    Pan, Zhiyu
    Hong, Chaoyi
    Cao, Zhiguo
    Zhong, Weicai
    2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 2640 - 2645
  • [50] Image steganalysis with multi-scale residual network
    Chen, Hao
    Han, Qi
    Li, Qiong
    Tong, Xiaojun
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (14) : 22009 - 22031