Deep laplacian pyramid networks for fast and accurate super-resolution

Wei Sheng Lai, Jia Bin Huang, Narendra Ahuja, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

318 Citations (Scopus)

Abstract

Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5835-5843
Number of pages9
ISBN (Electronic)9781538604571
DOIs
Publication statusPublished - 2017 Nov 6
Event30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 - Honolulu, United States
Duration: 2017 Jul 212017 Jul 26

Publication series

NameProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Volume2017-January

Other

Other30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
CountryUnited States
CityHonolulu
Period17/7/2117/7/26

Fingerprint

Image resolution
Convolution
Computational complexity
Interpolation
Neural networks
Processing

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Lai, W. S., Huang, J. B., Ahuja, N., & Yang, M. H. (2017). Deep laplacian pyramid networks for fast and accurate super-resolution. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 5835-5843). (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CVPR.2017.618
Lai, Wei Sheng ; Huang, Jia Bin ; Ahuja, Narendra ; Yang, Ming Hsuan. / Deep laplacian pyramid networks for fast and accurate super-resolution. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 5835-5843 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017).
@inproceedings{ece73a5bae9f43a4a81bae75534c9336,
title = "Deep laplacian pyramid networks for fast and accurate super-resolution",
abstract = "Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.",
author = "Lai, {Wei Sheng} and Huang, {Jia Bin} and Narendra Ahuja and Yang, {Ming Hsuan}",
year = "2017",
month = "11",
day = "6",
doi = "10.1109/CVPR.2017.618",
language = "English",
series = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "5835--5843",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017",
address = "United States",

}

Lai, WS, Huang, JB, Ahuja, N & Yang, MH 2017, Deep laplacian pyramid networks for fast and accurate super-resolution. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 5835-5843, 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPR.2017.618

Deep laplacian pyramid networks for fast and accurate super-resolution. / Lai, Wei Sheng; Huang, Jia Bin; Ahuja, Narendra; Yang, Ming Hsuan.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 5835-5843 (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Deep laplacian pyramid networks for fast and accurate super-resolution

AU - Lai, Wei Sheng

AU - Huang, Jia Bin

AU - Ahuja, Narendra

AU - Yang, Ming Hsuan

PY - 2017/11/6

Y1 - 2017/11/6

N2 - Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.

AB - Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85041899955&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041899955&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2017.618

DO - 10.1109/CVPR.2017.618

M3 - Conference contribution

AN - SCOPUS:85041899955

T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

SP - 5835

EP - 5843

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Lai WS, Huang JB, Ahuja N, Yang MH. Deep laplacian pyramid networks for fast and accurate super-resolution. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5835-5843. (Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017). https://doi.org/10.1109/CVPR.2017.618