A GPU-based matting Laplacian solver for high resolution image matting

被引：2
|
作者：
Mengcheng Huang
Fang Liu
Enhua Wu
机构：
[1] Chinese Academy of Sciences,State Key Lab of Computer Science, Institute of Software
[2] Graduate University of Chinese Academy of Sciences,Department of Computer and Information Science, Faculty of Science and Technology
[3] University of Macau,undefined
来源：
The Visual Computer | 2010年 / 26卷
关键词：
Image matting; Matting Laplacian; Conjugate gradient solver; GPU;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The recently proposed matting Laplacian (Levin et al., IEEE Trans. Pattern Anal. Mach. Intell. 30(2):228–242, 2008) has been proven to be a state-of-the-art method for solving the image matting problem. Using this method, matting is formulated as solving a high-order linear system which is hard-constrained by the input trimap. The main drawback of this method, however, is the high computational cost. As the size of the input image increases, the matting Laplacian becomes expensive to solve in terms of both memory and computational time.
引用
收藏
页码：943 / 950
页数：7
相关论文
共 50 条
  • [21] Adaptive propagation matting based on transparency of image
    Xiangyu Zhu
    Ping Wang
    Zhenghai Huang
    Multimedia Tools and Applications, 2018, 77 : 19089 - 19112
  • [22] SALIENCY-BASED UNSUPERVISED IMAGE MATTING
    Tan, Guanghua
    Qi, Jun
    Gao, Chunming
    Chen, Jin
    Zhuo, Liyuan
    INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2014, 28 (04)
  • [23] Image Matting Based on Deep Equilibrium Models
    Liu, Xinshuang
    Zhao, Yue
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING-ICANN 2024, PT II, 2024, 15017 : 379 - 391
  • [24] Natural image matting based on neighbor embedding
    Won, Kwang Hee
    Park, Soon-Yong
    Jung, Soon Ki
    COMPUTER VISION/COMPUTER GRAPHICS COLLABORATION TECHNIQUES, 2007, 4418 : 449 - +
  • [25] High resolution matting via interactive trimap segmentation
    Rhemann, Christoph
    Rother, Carsten
    Rav-Acha, Alex
    Sharp, Toby
    2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, : 775 - +
  • [26] Multimodal Image Fusion Method Based on Multiscale Image Matting
    Maqsood, Sarmad
    Damasevicius, Robertas
    Silka, Jakub
    Wozniak, Marcin
    ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING (ICAISC 2021), PT II, 2021, 12855 : 57 - 68
  • [27] Divide and Conquer: A Self-Adaptive Approach for High-Resolution Image Matting
    Cao, Guangying
    Li, Jianwei
    Chen, Xiaowu
    He, Zhiqiang
    2016 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND VISUALIZATION (ICVRV 2016), 2016, : 24 - 30
  • [28] Shadow verification based on feature matching and image matting
    Zhang, Liang
    He, Xiaomei
    Haili Wang
    Information Technology Journal, 2013, 12 (03) : 518 - 521
  • [29] Text Image Super-resolution by Image Matting and Text Label Supervision
    Lin, Kai
    Liu, Yubao
    Li, Thomas H.
    Liu, Shan
    Li, Ge
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 1722 - 1727
  • [30] Image matting based on local color discrimination by SVM
    Hosaka, Tadaaki
    Kobayashi, Takumi
    Otsu, Nobuyuki
    PATTERN RECOGNITION LETTERS, 2009, 30 (14) : 1253 - 1263
12345