Face completion with Hybrid Dilated Convolution |
| |
Affiliation: | 1. Northeastern University, College of Information Science and Engineering, Shenyang 110819, China;2. Intelligent Systems Research Centre, University of Ulster, Londonderry, UK;3. University of California, Riverside, CA 92521, United States;1. College of Information Science and Engineering, China University of Petroleum (Beijing), Beijing, China;2. Key Lab of Petroleum Data Mining, China University of Petroleum (Beijing), Beijing, China;3. School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada;4. Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data, North China University of Technology, Beijing, China;5. School of Computer Science, North China University of Technology, Beijing, China |
| |
Abstract: | Image completion is a challenging task which aims to fill the missing or masked regions in images with plausibly synthesized contents. In this paper, we focus on face image inpainting tasks, aiming at reconstructing missing or damaged regions of an incomplete face image given the context information. We specially design the U-Net architecture to tackle the problem. The proposed U-Net based method combines Hybrid Dilated Convolution (HDC) and spectral normalization to fill in missing regions of any shape with sharp structures and fine-detailed textures. We perform both qualitative and quantitative evaluation on two challenging face datasets. Experimental results demonstrate that our method outperforms previous learning-based inpainting methods. The proposed method can generate realistic and semantically plausible images. |
| |
Keywords: | Image completion Image inpainting Deep learning GAN |
本文献已被 ScienceDirect 等数据库收录! |
|