Gated fusion network for joint image deblurring and super-resolution

Xinyi Zhang, Hang Dong, Zhe Hu, Wei Sheng Lai, Fei Wang, Ming Hsuan Yang

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be amplified by super-resolution methods. Image blur is a common degradation source. Images captured by moving or still cameras are inevitably affected by motion blur due to relative movements between sensors and objects. In this work, we focus on the super-resolution task with the presence of motion blur. We propose a deep gated fusion convolution neural network to generate a clear high-resolution frame from a single natural image with severe blur. By decomposing the feature extraction step into two task-independent streams, the dual-branch design can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. Extensive experiments demonstrate that our method generates sharper super-resolved images from low-resolution inputs with high computational efficiency.

Original languageEnglish
Publication statusPublished - 2019 Jan 1
Event29th British Machine Vision Conference, BMVC 2018 - Newcastle, United Kingdom
Duration: 2018 Sep 32018 Sep 6

Conference

Conference29th British Machine Vision Conference, BMVC 2018
CountryUnited Kingdom
CityNewcastle
Period18/9/318/9/6

Fingerprint

Fusion reactions
Degradation
Computational efficiency
Convolution
Image quality
Feature extraction
Pixels
Cameras
Neural networks
Sensors
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Zhang, X., Dong, H., Hu, Z., Lai, W. S., Wang, F., & Yang, M. H. (2019). Gated fusion network for joint image deblurring and super-resolution. Paper presented at 29th British Machine Vision Conference, BMVC 2018, Newcastle, United Kingdom.
Zhang, Xinyi ; Dong, Hang ; Hu, Zhe ; Lai, Wei Sheng ; Wang, Fei ; Yang, Ming Hsuan. / Gated fusion network for joint image deblurring and super-resolution. Paper presented at 29th British Machine Vision Conference, BMVC 2018, Newcastle, United Kingdom.
@conference{7f1be699cc5941e3a085bbf3d7f8e773,
title = "Gated fusion network for joint image deblurring and super-resolution",
abstract = "Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be amplified by super-resolution methods. Image blur is a common degradation source. Images captured by moving or still cameras are inevitably affected by motion blur due to relative movements between sensors and objects. In this work, we focus on the super-resolution task with the presence of motion blur. We propose a deep gated fusion convolution neural network to generate a clear high-resolution frame from a single natural image with severe blur. By decomposing the feature extraction step into two task-independent streams, the dual-branch design can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. Extensive experiments demonstrate that our method generates sharper super-resolved images from low-resolution inputs with high computational efficiency.",
author = "Xinyi Zhang and Hang Dong and Zhe Hu and Lai, {Wei Sheng} and Fei Wang and Yang, {Ming Hsuan}",
year = "2019",
month = "1",
day = "1",
language = "English",
note = "29th British Machine Vision Conference, BMVC 2018 ; Conference date: 03-09-2018 Through 06-09-2018",

}

Zhang, X, Dong, H, Hu, Z, Lai, WS, Wang, F & Yang, MH 2019, 'Gated fusion network for joint image deblurring and super-resolution' Paper presented at 29th British Machine Vision Conference, BMVC 2018, Newcastle, United Kingdom, 18/9/3 - 18/9/6, .

Gated fusion network for joint image deblurring and super-resolution. / Zhang, Xinyi; Dong, Hang; Hu, Zhe; Lai, Wei Sheng; Wang, Fei; Yang, Ming Hsuan.

2019. Paper presented at 29th British Machine Vision Conference, BMVC 2018, Newcastle, United Kingdom.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Gated fusion network for joint image deblurring and super-resolution

AU - Zhang, Xinyi

AU - Dong, Hang

AU - Hu, Zhe

AU - Lai, Wei Sheng

AU - Wang, Fei

AU - Yang, Ming Hsuan

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be amplified by super-resolution methods. Image blur is a common degradation source. Images captured by moving or still cameras are inevitably affected by motion blur due to relative movements between sensors and objects. In this work, we focus on the super-resolution task with the presence of motion blur. We propose a deep gated fusion convolution neural network to generate a clear high-resolution frame from a single natural image with severe blur. By decomposing the feature extraction step into two task-independent streams, the dual-branch design can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. Extensive experiments demonstrate that our method generates sharper super-resolved images from low-resolution inputs with high computational efficiency.

AB - Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be amplified by super-resolution methods. Image blur is a common degradation source. Images captured by moving or still cameras are inevitably affected by motion blur due to relative movements between sensors and objects. In this work, we focus on the super-resolution task with the presence of motion blur. We propose a deep gated fusion convolution neural network to generate a clear high-resolution frame from a single natural image with severe blur. By decomposing the feature extraction step into two task-independent streams, the dual-branch design can facilitate the training process by avoiding learning the mixed degradation all-in-one and thus enhance the final high-resolution prediction results. Extensive experiments demonstrate that our method generates sharper super-resolved images from low-resolution inputs with high computational efficiency.

UR - http://www.scopus.com/inward/record.url?scp=85072022815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072022815&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85072022815

ER -

Zhang X, Dong H, Hu Z, Lai WS, Wang F, Yang MH. Gated fusion network for joint image deblurring and super-resolution. 2019. Paper presented at 29th British Machine Vision Conference, BMVC 2018, Newcastle, United Kingdom.