Timezone: »

 
Poster
Deep Convolutional Neural Network for Image Deconvolution
Li Xu · Jimmy S. Ren · Ce Liu · Jiaya Jia

Wed Dec 10 04:00 PM -- 08:59 PM (PST) @ Level 2, room 210D #None
in Poster Session »

Many fundamental image-related problems involve deconvolution operators. Real blur degradation seldom complies with an deal linear convolution model due to camera noise, saturation, image compression, to name a few. Instead of perfectly modeling outliers, which is rather challenging from a generative model perspective, we develop a deep convolutional neural network to capture the characteristics of degradation. We note directly applying existing deep neural networks does not produce reasonable results. Our solution is to establish the connection between traditional optimization-based schemes and a neural network architecture where a novel, separable structure is introduced as a reliable support for robust deconvolution against artifacts. Our network contains two submodules, both trained in a supervised manner with proper initialization. They yield decent performance on non-blind image deconvolution compared to previous generative-model based methods.

Author Information

Li Xu (Lenovo IVCL)
Jimmy S. Ren (SenseTime Group Limited)
Ce Liu (Microsoft Research)
Jiaya Jia (CUHK)

More from the Same Authors