Globally and locally consistent image completion
Indexed incrossref
Abstract
We present a novel approach for image completion that results in images that are both locally and globally consistent. With a fully-convolutional neural network, we can complete images of arbitrary resolutions by filling-in missing regions of any shape. To train this image completion network to be consistent, we use global and local context discriminators that are trained to distinguish real images from completed ones. The global discriminator looks at the entire image to assess if it is coherent as a whole, while the local discriminator looks only at a small area centered at the completed region to ensure the local consistency of the generated patches. The image completion network is then trained to fool the…
Citation impact
2,293
total citations
- FWCI
- 79.66
- Percentile
- 100%
- References
- 55
Citations per year
Authors
3Topics & keywords
Topics
Keywords
- Discriminator
- Image (mathematics)
- Artificial intelligence
- Consistency (knowledge bases)
- Computer science
- Context (archaeology)
- Convolutional neural network
- Contrast (vision)
UN Sustainable Development Goals
- Reduced inequalities
No related works found for this paper.