Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled to the high resolution (HR) space using a single filter, commonly bicubic interpolation, before reconstruction. This means that the super-resolution (SR) operation is performed in HR space. We demonstrate that this is sub-optimal and adds computational complexity. In this paper, we present the first convolutional neural network (CNN) capable of real-time SR of 1080p videos on a single K2 GPU. To achieve this, we propose a novel CNN architecture where the feature maps are extracted in the LR space. In addition, we introduce an efficient sub-pixel convolution layer which learns an array of upscaling filters to upscale the final LR feature maps into the HR output. By doing so, we effectively replace the handcrafted bicubic filter in the SR pipeline with more complex upscaling filters specifically trained for each feature map, whilst also reducing the computational complexity of the overall SR operation. We evaluate the proposed approach using images and videos from publicly available datasets and show that it performs significantly better (+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude faster than previous CNN-based methods.
Date Issued
2016-06-26
Date Acceptance
2016-03-02
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, pp.1874-1883
ISBN
9781467388511
ISSN
1063-6919
Publisher
IEEE
Start Page
1874
End Page
1883
Journal / Book Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Copyright Statement
© 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Source
CVPR 2016
Publication Status
Published
Start Date
2016-06-27
Finish Date
2016-06-30
Coverage Spatial
Las Vegas, NV, USA