A traditional image pyramid is an effective way to extract multiscale features. However, for image restoration, downsampling and upsampling lose details in the original resolution and result in an over smooth result. To overcome this defect, we propose a receptive pyramid (RP) that replaces downsampling by dilated convolution to extract multiscale features on the original resolution and make a full resolution correction. We present an RP-based convolution neural network named receptive pyramid convolutional network (RPCN) for efficient color image compression artifact reduction (CAR). Specifically, we propose residual connected convolution blocks as the baseline of RPCN. RPs work in convolution blocks to extract the hierarchical multiscale features for local feature correction. Moreover, the global feature fusion and vector correction are also introduced to further exploit the hierarchical features from the baseline. Benefiting from the RP, our RPCN achieves state-of-the-art performance with a much smaller model and much faster running speed for the CAR task. |
ACCESS THE FULL ARTICLE
No SPIE Account? Create one
' + document.title + '
');
mywindow.document.write('' + document.getElementById('divARTICLECONTENTTop').innerHTML + '
');
mywindow.document.close(); // necessary for IE >= 10
mywindow.focus(); // necessary for IE >= 10*/
// mywindow.print();
};
CITATIONS
Cited by 2 scholarly publications.
Convolution
Image compression
Image processing
Image restoration
Image resolution
Neural networks
Super resolution