Abstract | ||
---|---|---|
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 in-painting and super-resolution is obtained where our system outperforms previous ones while keeping the running time competitive. |
Year | Venue | Field |
---|---|---|
2015 | Annual Conference on Neural Information Processing Systems | Computer science,Convolutional neural network,Interpolation,Filter (signal processing),Deconvolution,Inpainting,Operator (computer programming),Artificial intelligence,Deep learning,Artificial neural network,Machine learning |
DocType | Volume | ISSN |
Conference | 28 | 1049-5258 |
Citations | PageRank | References |
18 | 0.82 | 13 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jimmy S. J. Ren | 1 | 324 | 23.85 |
Li Xu | 2 | 1713 | 54.04 |
Qiong Yan | 3 | 630 | 22.47 |
Wenxiu Sun | 4 | 160 | 20.79 |