Sub-Pixel Back-Projection Network For Lightweight Single Image Super-Resolution
Item Type:Conference Paper
Citation:Supratik Banerjee Cagri Ozcinar, Aakanksha Rana Aljosa Smolic Michael Manzke, Sub-Pixel Back-Projection Network For Lightweight Single Image Super-Resolution, The 2020 Irish Machine Vision and Image Processing Conference (IMVIP 2020) is hosted online this year by IT Sligo Sligo, 2020., 2020
2008.01116v1.pdf (PDF) 5.079Mb
Convolutional neural network (CNN)-based methods have achieved great success for single-image superresolution (SISR). However, most models attempt to improve reconstruction accuracy while increasing the requirement of number of model parameters. To tackle this problem, in this paper, we study reducing the number of parameters and computational cost of CNN-based SISR methods while maintaining the accuracy of super-resolution reconstruction performance. To this end, we introduce a novel network architecture for SISR, which strikes a good trade-off between reconstruction quality and low computational complexity. Specifically, we propose an iterative back-projection architecture using sub-pixel convolution instead of deconvolution layers. We evaluate the performance of computational and reconstruction accuracy for our proposed model with extensive quantitative and qualitative evaluations. Experimental results reveal that our proposed method uses fewer parameters and reduces the computational cost while maintaining reconstruction accuracy against state-of-the-art SISR methods over well-known four SR benchmark datasets. Code is available at "https://github.com/supratikbanerjee/SubPixel-BackProjection_SuperResolution".
Science Foundation Ireland (SFI)
IMVIP Conference does not issue DOIs for their conference papers. There is no page number, page range to add either. Can this output still be recorded on the RSS/TARA and calendar? We have a few IMVIP publications in the V-SENSE outputs.
Other Titles:The 2020 Irish Machine Vision and Image Processing Conference (IMVIP 2020) is hosted online this year by IT Sligo Sligo, 2020.
Type of material:Conference Paper
Availability:Full text available
Keywords:Super-Resolution, Convolutional neural network, Sub-pixel convolution, Iterative back-projection
Subject (TCD):Creative Technologies , Digital Engagement , Computer Education/Literacy , Information technology in education , Multimedia & Creativity