Generic 3D Convolutional Fusion for Image Restoration

被引:1
|
作者
Wu, Jiqing [1 ]
Timofte, Radu [1 ]
Gool, Luc Van [1 ]
机构
[1] Swiss Fed Inst Technol, D ITET, Comp Vis Lab, Zurich, Switzerland
来源
关键词
D O I
10.1007/978-3-319-54407-6_11
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ in their formulations and assumptions, so even if their average performance may be similar, some work better on certain image types and image regions than others. This complementarity motivated us to propose a novel 3D convolutional fusion (3DCF) method. Unlike other methods adapted to different tasks, our method uses the exact same convolutional network architecture to address both image denoising and single image super-resolution. Our 3DCF method achieves substantial improvements (0.1 dB-0.4 dB PSNR) over the state-of-the-art methods that it fuses on standard benchmarks for both tasks. At the same time, the method still is computationally efficient.
引用
收藏
页码:159 / 176
页数:18
相关论文
共 50 条
  • [1] 3D Image Restoration using Diffusion and Fusion Techniques
    Terebes, Romulus
    Pop, Sorin
    Borda, Monica
    Ludusan, Cosmin
    Lavialle, Olivier
    [J]. PROCEEDINGS ELMAR-2010, 2010, : 37 - 40
  • [2] Division and Fusion: Rethink Convolutional Kernels for 3D Medical Image Segmentation
    Fang, Xi
    Sanford, Thomas
    Turkbey, Baris
    Xu, Sheng
    Wood, Bradford J.
    Yan, Pingkun
    [J]. MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2020, 2020, 12436 : 160 - 169
  • [3] 3D CONVOLUTIONAL NEURAL NETWORKS BY MODAL FUSION
    Yoshiyasu, Yusuke
    Yoshida, Eiichi
    Pirk, Soeren
    Guibas, Leonidas
    [J]. 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 1777 - 1781
  • [4] Occlusion Detection and Image Restoration in 3D Face Image
    Srinivasan, A.
    Balamurugan, V
    [J]. TENCON 2014 - 2014 IEEE REGION 10 CONFERENCE, 2014,
  • [5] Image fusion and multimodality 3D imaging
    Pelizzari, CA
    [J]. COMPUTER-AIDED DIAGNOSIS IN MEDICAL IMAGING, 1999, 1182 : 453 - 461
  • [6] 3D Convolutional Network Based Foreground Feature Fusion
    Song, Hanjian
    Tian, Lihua
    Li, Chen
    [J]. 2018 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM 2018), 2018, : 253 - 258
  • [7] A review on 3D image reconstruction on specific and generic objects
    Shalma, H.
    Selvaraj, P.
    [J]. Materials Today: Proceedings, 2023, 80 : 2400 - 2405
  • [8] Image Segmentation in 3D Brachytherapy Using Convolutional LSTM
    Chang, Jui-Hung
    Lin, Kai-Hsiang
    Wang, Ti-Hao
    Zhou, Yu-Kai
    Chung, Pau-Choo
    [J]. JOURNAL OF MEDICAL AND BIOLOGICAL ENGINEERING, 2021, 41 (05) : 636 - 651
  • [9] Fenestrated EVAR With 3D CTA Image Fusion
    Schermerhorn, Marc L.
    [J]. JOURNAL OF VASCULAR SURGERY, 2016, 63 (06) : 230S - 230S
  • [10] Image Segmentation in 3D Brachytherapy Using Convolutional LSTM
    Jui-Hung Chang
    Kai-Hsiang Lin
    Ti-Hao Wang
    Yu-Kai Zhou
    Pau-Choo Chung
    [J]. Journal of Medical and Biological Engineering, 2021, 41 : 636 - 651