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
  • [1] Multi-Focus Image Fusion Based on Multi-Scale Gradients and Image Matting
    Chen, Jun
    Li, Xuejiao
    Luo, Linbo
    Ma, Jiayi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2022, 24 : 655 - 667
  • [2] Pyramid Matting: A Resource-Adaptive Multi-Scale Pixel Pair Optimization Framework for Image Matting
    Liang Yihui
    Feng Fujian
    Cai Zhaoquan
    IEEE ACCESS, 2020, 8 : 93487 - 93498
  • [3] Multi-scale depth information fusion network for image dehazing
    Fan, Guodong
    Hua, Zhen
    Li, Jinjiang
    APPLIED INTELLIGENCE, 2021, 51 (10) : 7262 - 7280
  • [4] Incorporating attentive multi-scale context information for image captioning
    Prudviraj, Jeripothula
    Sravani, Yenduri
    Mohan, C. Krishna
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (07) : 10017 - 10037
  • [5] Incorporating attentive multi-scale context information for image captioning
    Jeripothula Prudviraj
    Yenduri Sravani
    C. Krishna Mohan
    Multimedia Tools and Applications, 2023, 82 : 10017 - 10037
  • [6] Multi-scale depth information fusion network for image dehazing
    Guodong Fan
    Zhen Hua
    Jinjiang Li
    Applied Intelligence, 2021, 51 : 7262 - 7280
  • [7] Hyperspectral image classification based on multi-scale information compensation
    Wang, Di
    Du, Bo
    Zhang, Liangpei
    Chu, Sheng
    REMOTE SENSING LETTERS, 2020, 11 (03) : 293 - 302
  • [8] Multi-scale Image Harmonization
    Sunkavalli, Kalyan
    Johnson, Micah K.
    Matusik, Wojciech
    Pfister, Hanspeter
    ACM TRANSACTIONS ON GRAPHICS, 2010, 29 (04):
  • [9] An Affinity Based Matting Method Based on Multi-Scale Space Fusion
    Yao, Guilin
    Jiang, Dongai
    Sun, Jianliang
    PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 1572 - 1577
  • [10] Multi-scale assembly with robot teams
    Dogar, Mehmet
    Knepper, Ross A.
    Spielberg, Andrew
    Choi, Changhyun
    Christensen, Henrik I.
    Rus, Daniela
    INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH, 2015, 34 (13): : 1645 - 1659