Timezone: »

 
Poster
Image Denoising and Inpainting with Deep Neural Networks
Junyuan Xie · Linli Xu · Enhong Chen

Thu Dec 06 02:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor
in Poster Session »

We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA). We propose an alternative training scheme that successfully adapts DA, originally designed for unsupervised feature learning, to the tasks of image denoising and blind inpainting. Our method achieves state-of-the-art performance in the image denoising task. More importantly, in blind image inpainting task, the proposed method provides solutions to some complex problems that have not been tackled before. Specifically, we can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random. Moreover, the proposed method does not need the information regarding the region that requires inpainting to be given a priori. Experimental results demonstrate the effectiveness of the proposed method in the tasks of image denoising and blind inpainting. We also show that our new training scheme for DA is more effective and can improve the performance of unsupervised feature learning.

[ PDF] 

Author Information

Junyuan Xie
Linli Xu (University of Science and Tech)
Enhong Chen (University of Science and Technology of China)

More from the Same Authors