iWave3D: End-to-end Brain Image Compression with Trainable 3-D Wavelet Transform

被引:3
|
作者
Xue, Dongmei [1 ]
Ma, Haichuan [1 ]
Li, Li [1 ]
Liu, Dong [1 ]
Xiong, Zhiwei [1 ]
机构
[1] Univ Sci & Technol China, Hefei, Peoples R China
关键词
Brain image compression; wavelet transform; lifting scheme; 3-D convolutional neural networks; LIFTING SCHEME; CONSTRUCTION;
D O I
10.1109/VCIP53242.2021.9675359
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the rapid development of whole brain imaging technology, a large number of brain images have been produced, which puts forward a great demand for efficient brain image compression methods. At present, the most commonly used compression methods are all based on 3-D wavelet transform, such as JP3D. However, traditional 3-D wavelet transforms are designed manually with certain assumptions on the signal, but brain images are not as ideal as assumed. What's more, they are not directly optimized for compression task. In order to solve these problems, we propose a trainable 3-D wavelet transform based on the lifting scheme, in which the predict and update steps are replaced by 3-D convolutional neural networks. Then the proposed transform is embedded into an end-to-end compression scheme called iWave3D, which is trained with a large amount of brain images to directly minimize the rate-distortion loss. Experimental results demonstrate that our method outperforms JP3D significantly by 2.012 dB in terms of average BD-PSNR.
引用
收藏
页数:5
相关论文
共 50 条
  • [31] Fast 3-D seismic adaptive compression using the lifted wavelet transform
    Khène, FM
    ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2004, 29 (2C) : 43 - 61
  • [32] Compression coding of color image via 3-D matrix transform
    Jilin Univ of Technology, Changchun, China
    Tien Tzu Hsueh Pao, 7 (16-21):
  • [33] 3-D warped discrete cosine transform for MRI image compression
    Prabhu, K. M. M.
    Sridhar, K.
    Mischi, M.
    Bharath, H. N.
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2013, 8 (01) : 50 - 58
  • [34] A 3-D BLOCK TRANSFORM BASED APPROACH TO COLOR IMAGE COMPRESSION
    Nath, V. K.
    Hazarika, D.
    Mahanta, A.
    2008 IEEE REGION 10 CONFERENCE: TENCON 2008, VOLS 1-4, 2008, : 2498 - +
  • [35] PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Clouds
    Wang, Sukai
    Sun, Yuxiang
    Liu, Chengju
    Liu, Ming
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2020, 5 (02) : 3206 - 3212
  • [36] End-to-end simulation of the C-ADS Injector II with a 3-D field map
    Wang Zhi-Jun
    He Yuan
    Wang Wang-Sheng
    Liu Shu-Hui
    Jia Huan
    Li Chao
    Xu Xian-Bo
    Chen Xi-Meng
    CHINESE PHYSICS C, 2013, 37 (04)
  • [37] An end-to-end workflow for nondestructive 3D pathology
    Bishop, Kevin W.
    Erion Barner, Lindsey A.
    Han, Qinghua
    Baraznenok, Elena
    Lan, Lydia
    Poudel, Chetan
    Gao, Gan
    Serafin, Robert B.
    Chow, Sarah S. L.
    Glaser, Adam K.
    Janowczyk, Andrew
    Brenes, David
    Huang, Hongyi
    Miyasato, Dominie
    True, Lawrence D.
    Kang, Soyoung
    Vaughan, Joshua C.
    Liu, Jonathan T. C.
    NATURE PROTOCOLS, 2024, 19 (04) : 1122 - 1148
  • [38] KeypointDETR: An End-to-End 3D Keypoint Detector
    Jin, Hairong
    Shen, Yuefan
    Lou, Jianwen
    Zhou, Kun
    Zheng, Youyi
    COMPUTER VISION - ECCV 2024, PT LXXIV, 2025, 15132 : 374 - 390
  • [39] End-to-end 3D Tracking with Decoupled Queries
    Li, Yanwei
    Yu, Zhiding
    Philion, Jonah
    Anandkumar, Anima
    Fidler, Sanja
    Jia, Jiaya
    Alvarez, Jose
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 18256 - 18265
  • [40] 3D Dosimetry in End-To-End Dosimetry QA
    Ibbott, G.
    MEDICAL PHYSICS, 2016, 43 (06) : 3695 - 3695