Skip to main content
Video s3
    Details
    Author(s)
    Display Name
    Dongmei Xue
    Affiliation
    Affiliation
    University of Science and Technology of China
    Display Name
    Cunhui Dong
    Affiliation
    Affiliation
    University of Science and Technology of China
    Display Name
    Fan Ye
    Affiliation
    Affiliation
    State Key Laboratory of ASIC & System, Fudan University
    Display Name
    Hang Chen
    Affiliation
    Affiliation
    University of Science and Technology of China
    Display Name
    Bowei Kang
    Affiliation
    Affiliation
    University of Science and Technology of China
    Display Name
    Li Li
    Affiliation
    Affiliation
    Nanjing University
    Display Name
    Dong Liu
    Affiliation
    Affiliation
    Hong Kong Polytechnic University
    Abstract

    In this paper, we propose an improved framework for iWave++ called iWavePro. iWavePro is designed with several techniques to overcome the problems mentioned above. These techniques are the joint multi-component Gaussian mixture entropy coding, the affine wavelet-like transform, and the online training. Experimental results show that our method can save 10.73\% bit rate compared with iWave++ at the same quality.