%0 Conference Proceedings
%T OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network
%A Parichehr Behjati Ardakani
%A Pau Rodriguez
%A Armin Mehri
%A Isabelle Hupont
%A Carles Fernandez
%A Jordi Gonzalez
%B IEEE Winter Conference on Applications of Computer Vision
%D 2021
%F Parichehr Behjati Ardakani2021
%O ISE; 600.119; 600.098
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3512), last updated on Mon, 24 Oct 2022 15:12:00 +0200
%X 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. More- over, 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-the-art approaches in standard benchmarks, while maintaining relatively low computation and memory requirements.
%U http://refbase.cvc.uab.es/files/BRM2021.pdf
%U http://dx.doi.org/10.1109/WACV48630.2021.00274
%P 2693-2702