Abstract

Recent deep learning based approaches have shown promising results for the challenging task of inpainting large missing regions in an image. These methods can generate visually plausible image structures and textures, but often create distorted structures or blurry textures inconsistent with surrounding areas. This is mainly due to ineffectiveness of convolutional neural networks in explicitly borrowing or copying information from distant spatial locations. On the other hand, traditional texture and patch synthesis approaches are particularly suitable when it needs to borrow textures from the surrounding regions. Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions. The model is a feedforward, fully convolutional neural network which can process images with multiple holes at arbitrary locations and with variable sizes during the test time. Experiments on multiple datasets including faces (CelebA, CelebA-HQ), textures (DTD) and natural images (ImageNet, Places2) demonstrate that our proposed approach generates higher-quality inpainting results than existing ones. Code, demo and models are available at: https://github.com/JiahuiYu/generative_inpainting.

Keywords

InpaintingComputer scienceArtificial intelligenceImage (mathematics)Convolutional neural networkGenerative grammarFilling-inProcess (computing)Pattern recognition (psychology)Generative modelTexture synthesisDeep learningCode (set theory)Texture (cosmology)Artificial neural networkComputer visionImage textureImage processingSet (abstract data type)

Affiliated Institutions

Related Publications

Publication Info

Year
2018
Type
article
Pages
5505-5514
Citations
2393
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

2393
OpenAlex

Cite This

Jiahui Yu, Zhe Lin, Shuicheng Yan et al. (2018). Generative Image Inpainting with Contextual Attention. , 5505-5514. https://doi.org/10.1109/cvpr.2018.00577

Identifiers

DOI
10.1109/cvpr.2018.00577