Corpus ID: 232035791

Image Completion via Inference in Deep Generative Models

@article{Harvey2021ImageCV,
  title={Image Completion via Inference in Deep Generative Models},
  author={William Harvey and Saeid Naderiparizi and Frank D. Wood},
  journal={ArXiv},
  year={2021},
  volume={abs/2102.12037}
}
We consider image completion from the perspective of amortized inference in an image generative model. We leverage recent state of the art variational auto-encoder architectures that have been shown to produce photo-realistic natural images at non-trivial resolutions. Through amortized inference in such a model we can train neural artifacts that produce diverse, realistic image completions even when the vast majority of an image is missing. We demonstrate superior sample quality and diversity… Expand

References

SHOWING 1-10 OF 43 REFERENCES
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
  • 18
  • Highly Influential
  • PDF
Pluralistic Image Completion
  • 105
  • Highly Influential
  • PDF
Context Encoders: Feature Learning by Inpainting
  • 2,460
  • Highly Influential
  • PDF
SGDR: Stochastic Gradient Descent with Warm Restarts
  • 1,443
  • Highly Influential
  • PDF
PatchMatch: a randomized correspondence algorithm for structural image editing
  • 1,240
  • Highly Influential
Near-Optimal Glimpse Sequences for Improved Hard Attention Neural Network Training
  • 1
  • PDF
NVAE: A Deep Hierarchical Variational Autoencoder
  • 69
  • PDF
Score-Based Generative Modeling through Stochastic Differential Equations
  • 21
  • PDF
UCTGAN: Diverse Image Inpainting Based on Unsupervised Cross-Space Translation
  • L. Zhao, Qihang Mo, +5 authors Dongming Lu
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
  • 14
  • PDF
A Style-Based Generator Architecture for Generative Adversarial Networks
  • 1,901
  • PDF
...
1
2
3
4
5
...