Deep learning has recently been introduced to the field of low-level computer vision and image processing. Promising results have been obtained in a number of tasks including super-resolution, inpainting, deconvolution, filtering, etc. However, previously adopted neural network approaches such as convolutional neural networks and sparse auto-encoders are inherently with translation invariant operators. We found this property prevents the deep learning approaches from outperforming the state-of-the-art if the task itself requires translation variant interpolation (TVI). In this paper, we draw on Shepard interpolation and design Shepard Convolutional Neural Networks (ShCNN) which efficiently realizes end-to-end trainable TVI operators in the network. We show that by adding only a few feature maps in the new Shepard layers, the network is able to achieve stronger results than a much deeper architecture. Superior performance on both image inpainting and super-resolution is obtained where our system outperforms previous ones while keeping the running time competitive.
Jimmy S. Ren (SenseTime Group Limited)
Li Xu (SenseTime Group Limited)
Qiong Yan (SenseTime Group Limited)
Wenxiu Sun (SenseTime Group Limited)
More from the Same Authors
2014 Poster: Deep Convolutional Neural Network for Image Deconvolution »
Li Xu · Jimmy S. Ren · Ce Liu · Jiaya Jia