Accurate Image Super-Resolution Using Very Deep Convolutional Networks

We present a highly accurate single-image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) s. 1646 - 1654
Hlavní autoři: Jiwon Kim, Jung Kwon Lee, Kyoung Mu Lee
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2016
Témata:
Convergence
Convolution
Image reconstruction
Signal resolution
Spatial resolution
Training
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We present a highly accurate single-image superresolution (SR) method. Our method uses a very deep convolutional network inspired by VGG-net used for ImageNet classification [19]. We find increasing our network depth shows a significant improvement in accuracy. Our final model uses 20 weight layers. By cascading small filters many times in a deep network structure, contextual information over large image regions is exploited in an efficient way. With very deep networks, however, convergence speed becomes a critical issue during training. We propose a simple yet effective training procedure. We learn residuals only and use extremely high learning rates (104 times higher than SRCNN [6]) enabled by adjustable gradient clipping. Our proposed method performs better than existing methods in accuracy and visual improvements in our results are easily noticeable.
ISSN:1063-6919
DOI:10.1109/CVPR.2016.182