Probabilistic Semantic Inpainting with Pixel Constrained CNNs
Abstract
Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics. Most semantic inpainting algorithms are deterministic: given an image with missing regions, a single inpainted image is generated. However, there are often several plausible inpaintings for a given missing region. In this paper, we propose a method to perform probabilistic semantic inpainting by building a model, based on PixelCNNs, that learns a distribution of images conditioned on a subset of visible pixels. Experiments on the MNIST and CelebA datasets show that our method produces diverse and realistic inpaintings.
Cite
Text
Dupont and Suresha. "Probabilistic Semantic Inpainting with Pixel Constrained CNNs." Artificial Intelligence and Statistics, 2019.Markdown
[Dupont and Suresha. "Probabilistic Semantic Inpainting with Pixel Constrained CNNs." Artificial Intelligence and Statistics, 2019.](https://mlanthology.org/aistats/2019/dupont2019aistats-probabilistic/)BibTeX
@inproceedings{dupont2019aistats-probabilistic,
title = {{Probabilistic Semantic Inpainting with Pixel Constrained CNNs}},
author = {Dupont, Emilien and Suresha, Suhas},
booktitle = {Artificial Intelligence and Statistics},
year = {2019},
pages = {2261-2270},
volume = {89},
url = {https://mlanthology.org/aistats/2019/dupont2019aistats-probabilistic/}
}