Image Inpainting via Generative Multi-Column Convolutional Neural Networks
Abstract
In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF regularization is adopted to enhance local details. The multi-column network combined with the reconstruction and MRF loss propagates local and global information derived from context to the target inpainting regions. Extensive experiments on challenging street view, face, natural objects and scenes manifest that our method produces visual compelling results even without previously common post-processing.
Cite
Text
Wang et al. "Image Inpainting via Generative Multi-Column Convolutional Neural Networks." Neural Information Processing Systems, 2018.Markdown
[Wang et al. "Image Inpainting via Generative Multi-Column Convolutional Neural Networks." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/wang2018neurips-image/)BibTeX
@inproceedings{wang2018neurips-image,
title = {{Image Inpainting via Generative Multi-Column Convolutional Neural Networks}},
author = {Wang, Yi and Tao, Xin and Qi, Xiaojuan and Shen, Xiaoyong and Jia, Jiaya},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {331-340},
url = {https://mlanthology.org/neurips/2018/wang2018neurips-image/}
}