OverNet : lightweight multi-scale super-resolution with overscaling network
Behjati, Parichehr (Centre de Visió per Computador (Bellaterra, Catalunya))
Rodriguez, Pau (Element AI (Montreal, Canadà))
Mehri, Armin (Centre de Visió per Computador (Bellaterra, Catalunya))
Hupont, Isabelle (Herta Security (Barcelona, Catalunya))
Fernández Tena, Carles (Herta Security (Barcelona, Catalunya))
Gonzàlez, Jordi (Centre de Visió per Computador (Bellaterra, Catalunya))

Data:	2021
Resum:	Super-resolution (SR) has achieved great success due to the development of deep convolutional neural networks (CNNs). However, as the depth and width of the networks increase, CNN-based SR methods have been faced with the challenge of computational complexity in practice. Moreover, most SR methods train a dedicated model for each target resolution, losing generality and increasing memory requirements. To address these limitations we introduce OverNet, a deep but lightweight convolutional network to solve SISR at arbitrary scale factors with a single model. We make the following contributions: first, we introduce a lightweight feature extractor that enforces efficient reuse of information through a novel recursive structure of skip and dense connections. Second, to maximize the performance of the feature extractor, we propose a model agnostic reconstruction module that generates accurate high-resolution images from overscaled feature maps obtained from any SR architecture. Third, we introduce a multi-scale loss function to achieve generalization across scales. Experiments show that our proposal outperforms previous state-of-theart approaches in standard benchmarks, while maintaining relatively low computation and memory requirements.
Ajuts:	Ministerio de Economía y Competitividad TIN2015-65464-R
Drets:	Tots els drets reservats.
Llengua:	Anglès
Document:	Comunicació de congrés ; recerca ; Versió acceptada per publicar
Matèria:	Training ; Computational modeling ; Superresolution ; Memory management ; Noise reduction ; Feature extraction ; Data mining
Publicat a:	2021 IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa, 2021

Adreça alternativa: https://arxiv.org/abs/2012.04578v1
DOI: 10.1109/WACV48630.2021.00274

Postprint 11 p, 5.2 MB

El registre apareix a les col·leccions:
Contribucions a jornades i congressos > Ponències i comunicacions > Ponències i comunicacions de la UAB