Single image super-resolution based on directional variance attention network
Behjati, Parichehr (Centre de Visió per Computador)
Rodríguez López, Pau (ServiceNow Research)
Fernández Tena, Carles (Oxolo GmbH)
Hupont, Isabelle (European Commission Joint Research Centre Sevilla)
Mehri, Armin (Centre de Visió per Computador)
Gonzàlez, Jordi (Universitat Autònoma de Barcelona)

Fecha:	2023
Descripción:	14 pàg.
Resumen:	Recent advances in single image super-resolution (SISR) explore the power of deep convolutional neural networks (CNNs) to achieve better performance. However, most of the progress has been made by scaling CNN architectures, which usually raise computational demands and memory consumption. This makes modern architectures less applicable in practice. In addition, most CNN-based SR methods do not fully utilize the informative hierarchical features that are helpful for final image recovery. In order to address these issues, we propose a directional variance attention network (DiVANet), a computationally efficient yet accurate network for SISR. Specifically, we introduce a novel directional variance attention (DiVA) mechanism to capture long-range spatial dependencies and exploit inter-channel dependencies simultaneously for more discriminative representations. Furthermore, we propose a residual attention feature group (RAFG) for parallelizing attention and residual block computation. The output of each residual block is linearly fused at the RAFG output to provide access to the whole feature hierarchy. In parallel, DiVA extracts most relevant features from the network for improving the final output and preventing information loss along the successive operations inside the network. Experimental results demonstrate the superiority of DiVANet over the state of the art in several datasets, while maintaining relatively low computation and memory footprint. The code is available at https://github. com/pbehjatii/DiVANet.
Ayudas:	Agencia Estatal de Investigación PID2020-120311RB-I00 Ministerio de Economía y Competitividad TIN2015-65464-R
Nota:	Altres ajuts: Isabelle Hupont's work is supported by the HUMAINT project of the European Commission's Joint Research Centre.
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Lengua:	Anglès
Documento:	Article ; recerca ; Versió acceptada per publicar
Materia:	Attention mechanism ; Efficient network ; Single image super-resolution
Publicado en:	Pattern Recognition, Vol. 133 (January 2023) , art. 108997, ISSN 0031-3203

DOI: 10.1016/j.patcog.2022.108997

Postprint 36 p, 6.7 MB

El registro aparece en las colecciones:
Artículos > Artículos de investigación
Artículos > Artículos publicados