ASDN: A Deep Convolutional Network for Arbitrary Scale Image Super-Resolution
- Publisher:
- Springer Science and Business Media LLC
- Publication Type:
- Journal Article
- Citation:
- Mobile Networks and Applications, 2021, 26, (1), pp. 13-26
- Issue Date:
- 2021-02-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
Shen2021_Article_ASDNADeepConvolutionalNetworkF.pdf | Published Version | 3.71 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Deep convolutional neural networks have significantly improved the peak signal-to-noise ratio of Super-Resolution (SR). However, image viewer applications commonly allow users to zoom the images to arbitrary magnification scales, thus far imposing a large number of required training scales at a tremendous computational cost. To obtain a more computationally efficient model for arbitrary-scale SR, this paper employs a Laplacian pyramid method to reconstruct any-scale high-resolution (HR) images using the high-frequency image details in a Laplacian Frequency Representation. For SR of small-scales (between 1 and 2), images are constructed by interpolation from a sparse set of precalculated Laplacian pyramid levels. SR of larger scales is computed by recursion from small scales, which significantly reduces the computational cost. For a full comparison, fixed- and any-scale experiments are conducted using various benchmarks. At fixed scales, ASDN outperforms predefined upsampling methods (e.g., SRCNN, VDSR, DRRN) by about 1 dB in PSNR. At any-scale, ASDN generally exceeds Meta-SR on many scales.
Please use this identifier to cite or link to this item: