Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/3624
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Deepak, Shashikant | - |
dc.contributor.author | Singh, Chanda | - |
dc.contributor.author | Patra, Dipti | - |
dc.date.accessioned | 2022-02-15T11:44:25Z | - |
dc.date.available | 2022-02-15T11:44:25Z | - |
dc.date.issued | 2021-12 | - |
dc.identifier.citation | INDICON 2021 on 19-21 December, 2021 at Guwahati, India (virtually). | en_US |
dc.identifier.uri | http://hdl.handle.net/2080/3624 | - |
dc.description | Copyright of this paper is with proceedings publisher | en_US |
dc.description.abstract | The Deep learning-based approach for solving the ill-posed problem of single image super-resolution reconstruction (SRR) has achieved tremendous success in recent times. However, not much work is carried out in the direction of blind image super-resolution, where the degradation kernel is said to be unknown. This paper addresses the said problem of blind single image super-resolution reconstruction using an alternative learning approach by training two convolutional neural networks. Most of the available model for blind super-resolution considers a fixed degradation kernel for reconstruction, which leads to drop in performance. Therefore a learnable kernel estimation approach is adopted by using a kernel-estimator network. Further, this estimated kernel is used to generate a super resolution image using a Generator network. To successfully model the reconstruction of vital features like edges and texture and to learn the inter-pixel dependencies between multi-level feature maps, we employ a densely residual Laplacian attention block (DLA-Block). The proposed method is extensively tested on real image and synthetic image data-sets. The experimental results have shown out-performance compared to the state-of the- art in terms of high reconstruction accuracy as well as PSNR and SSIM. | en_US |
dc.language.iso | en | en_US |
dc.subject | Blind super resolution | en_US |
dc.subject | Iterative network | en_US |
dc.subject | Debluring | en_US |
dc.subject | kernel estimation | en_US |
dc.title | Iterative Dense Network using Laplacian Pyramid Model for Blind Super Resolution | en_US |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
PATRA,D_IEEE INDICON2021.pdf | 4.42 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.