… INTRODUCTION SINGLE imagesuper-resolution is usually cast as an … fully convolutional neural network to directly learn the mapping from the input LR image and the output HR image. …
J Jiang, J Ma, C Chen, X Jiang… - IEEE transactions on …, 2016 - ieeexplore.ieee.org
… )-based face imagesuper-resolution approaches are able to … a novel SR-based face image superresolution approach that … aim at learning the direct mapping function from the LR space …
… In this paper, we introduce a robust GAN for imagesuperresolution to be able to mitigate the … to produce 200 feature maps as the first convolutional layer and 300 feature maps as the …
L Chen, J Pan, Q Li - IEEE Transactions on Image Processing, 2019 - ieeexplore.ieee.org
… mainly map the whole LR image to the whole HR image, while the algorithms based on the local structure map … Her research interests include imagesuperresolution and related vision …
Y Romano, J Isidoro, P Milanfar - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
… resolution images) we can learn set of filters (ie a mapping) … to be used in order to obtain a reliable estimate. In fact, we … Single ImageSuper-Resolution In this subsection we compare …
Y Zhou, X Du, M Wang, S Huo… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
… It is commonly recognized that these tasks have strong … up sample the LR feature maps in an approach, which is also … an ablation study on the imagesuper-resolution task. Table I lists …
F Zhang, N Cai, G Cen, F Li, H Wang, X Chen - Signal Processing: Image …, 2018 - Elsevier
… in the field of single imagesuper-resolution (SR) compared with … LR images, we propose a multi-scale feature mapping scheme … Robust single imagesuper-resolution via deep networks …
… Learning-based single imagesuper-resolution (SISR) … of a data term and a prior term under the MAPframework. … Therefore, it is necessary to further analyze the kernel robustness of …
Y Zhang, Y Tian, Y Kong… - Proceedings of the …, 2018 - openaccess.thecvf.com
… Single imageSuper-Resolution (SISR) aims to generate a … interpolated LR images, failing to establish an end-to-end mapping from … the effectiveness and robustness of our RDN model. …