Joint Spatial-Wavelet Dual-Stream Network for Super-Resolution
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Joint Spatial-Wavelet Dual-Stream Network for Super-Resolution. / Chen, Zhen; Guo, Xiaoqing; Yang, Chen; Ibragimov, Bulat; Yuan, Yixuan.
Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 - 23rd International Conference, Proceedings. ed. / Anne L. Martel; Purang Abolmaesumi; Danail Stoyanov; Diana Mateus; Maria A. Zuluaga; S. Kevin Zhou; Daniel Racoceanu; Leo Joskowicz. Springer VS, 2020. p. 184-193 (Lecture Notes in Computer Science, Vol. 12265 LNCS).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Joint Spatial-Wavelet Dual-Stream Network for Super-Resolution
AU - Chen, Zhen
AU - Guo, Xiaoqing
AU - Yang, Chen
AU - Ibragimov, Bulat
AU - Yuan, Yixuan
N1 - Publisher Copyright: © 2020, Springer Nature Switzerland AG.
PY - 2020
Y1 - 2020
N2 - Super-Resolution (SR) techniques can compensate for the missing information of low-resolution images and further promote experts and algorithms to make accurate diagnosis decisions. Although the existing pixel-loss based SR works produce high-resolution images with impressive objective metrics, the over-smoothed contents that lose high-frequency information would disturb the visual experience and the subsequent diagnosis. To address this issue, we propose a joint Spatial-Wavelet super-resolution Network (SWD-Net) with collaborative Dual-stream. In the spatial stage, a Refined Context Fusion (RCF) is proposed to iteratively rectify the features by a counterpart stream with compensative receptive fields. After that, the wavelet stage enhances the reconstructed images, especially the structural boundaries. Specifically, we design the tailor-made Wavelet Features Adaptation (WFA) to adjust the wavelet coefficients for better compatibility with networks and Wavelet-Aware Convolutional blocks (WAC) to exploit features in the wavelet domain efficiently. We further introduce the wavelet coefficients supervision together with the traditional spatial loss to jointly optimize the network and obtain the high-frequency enhanced SR images. To evaluate the SR for medical images, we build a benchmark dataset with histopathology images and evaluate the proposed SWD-Net under different settings. The comprehensive experiments demonstrate our SWD-Net outperforms state-of-the-art methods. Furthermore, SWD-Net is proven to promote medical image diagnosis with a large margin. The source code and dataset are available at https://github.com/franciszchen/SWD-Net.
AB - Super-Resolution (SR) techniques can compensate for the missing information of low-resolution images and further promote experts and algorithms to make accurate diagnosis decisions. Although the existing pixel-loss based SR works produce high-resolution images with impressive objective metrics, the over-smoothed contents that lose high-frequency information would disturb the visual experience and the subsequent diagnosis. To address this issue, we propose a joint Spatial-Wavelet super-resolution Network (SWD-Net) with collaborative Dual-stream. In the spatial stage, a Refined Context Fusion (RCF) is proposed to iteratively rectify the features by a counterpart stream with compensative receptive fields. After that, the wavelet stage enhances the reconstructed images, especially the structural boundaries. Specifically, we design the tailor-made Wavelet Features Adaptation (WFA) to adjust the wavelet coefficients for better compatibility with networks and Wavelet-Aware Convolutional blocks (WAC) to exploit features in the wavelet domain efficiently. We further introduce the wavelet coefficients supervision together with the traditional spatial loss to jointly optimize the network and obtain the high-frequency enhanced SR images. To evaluate the SR for medical images, we build a benchmark dataset with histopathology images and evaluate the proposed SWD-Net under different settings. The comprehensive experiments demonstrate our SWD-Net outperforms state-of-the-art methods. Furthermore, SWD-Net is proven to promote medical image diagnosis with a large margin. The source code and dataset are available at https://github.com/franciszchen/SWD-Net.
KW - Convolutional neural networks
KW - Super-resolution
KW - Wavelet domain
UR - http://www.scopus.com/inward/record.url?scp=85092733435&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-59722-1_18
DO - 10.1007/978-3-030-59722-1_18
M3 - Article in proceedings
AN - SCOPUS:85092733435
SN - 9783030597214
T3 - Lecture Notes in Computer Science
SP - 184
EP - 193
BT - Medical Image Computing and Computer Assisted Intervention – MICCAI 2020 - 23rd International Conference, Proceedings
A2 - Martel, Anne L.
A2 - Abolmaesumi, Purang
A2 - Stoyanov, Danail
A2 - Mateus, Diana
A2 - Zuluaga, Maria A.
A2 - Zhou, S. Kevin
A2 - Racoceanu, Daniel
A2 - Joskowicz, Leo
PB - Springer VS
T2 - 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020
Y2 - 4 October 2020 through 8 October 2020
ER -
ID: 271604171