Image Inpainting Using Wasserstein Generative Adversarial Imputation Network

@inproceedings{Vasata2021ImageIU,
  title={Image Inpainting Using Wasserstein Generative Adversarial Imputation Network},
  author={Daniel Vasata and Tom{\'a}s Halama and Magda Friedjungov{\'a}},
  booktitle={International Conference on Artificial Neural Networks},
  year={2021}
}
Image inpainting is one of the important tasks in computer vision which focuses on the reconstruction of missing regions in an image. The aim of this paper is to introduce an image inpainting model based on Wasserstein Generative Adversarial Imputation Network. The generator network of the model uses building blocks of convolutional layers with different dilation rates, together with skip connections that help the model reproduce fine details of the output. This combination yields a universal… 

A Wasserstein GAN for Joint Learning of Inpainting and its Spatial Optimisation

This work proposes the first generative adversarial network (GAN) for spatial inpainting data optimisation, which allows joint training of an inPainting generator and a corresponding mask optimisation network and yields improvements in visual quality and speed over conven-tional stochastic models.

Learning Sparse Masks for Diffusion-based Image Inpainting

By emulating the complete inPainting pipeline with two networks for mask generation and neural surrogate inpainting, this work obtains a model for highly adaptive adaptive mask generation that can achieve competitive quality with an acceleration by as much as four orders of magnitude.

Deep Spatial and Tonal Data Optimisation for Homogeneous Diffusion Inpainting

Without the need for a single inpainting during test time, this deep optimisation accelerates data selection by more than four orders of magnitude compared to common model-based approaches and provides real-time performance with high quality results.

References

SHOWING 1-10 OF 27 REFERENCES

Image inpainting using Wasserstein Generative Adversarial Network

This work uses a convolution neural networks architecture with Atrous Spatial Pyramid Pooling module, which can obtain multi-scale objection information, to be the inpainting network and uses global and local Wasserstein discriminators that are jointly trained to distinguish real images from completed ones.

PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting

This work proposes a novel deep generative model equipped with a brand new style extractor which can extract the style feature (latent vector) from the ground truth andCrafts a consistency loss that guides the generated image to approximate the groundtruth.

Generative Image Inpainting with Contextual Attention

This work proposes 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.

PEPSI++: Fast and Lightweight Network for Image Inpainting

Diet-PEPSI is proposed, which aims at reducing the hardware costs and improving the inpainting performance, and novel rate-adaptive dilated convolutional layers that employ the common weights but produce dynamic features depending on the given dilation rates.

Context Encoders: Feature Learning by Inpainting

It is found that a context encoder learns a representation that captures not just appearance but also the semantics of visual structures, and can be used for semantic inpainting tasks, either stand-alone or as initialization for non-parametric methods.

A bi-level view of inpainting - based image compression

The Laplacian interpolation based compression model is revisited and two fast algorithms are introduced, namely successive preconditioning primal dual algorithm and the recently proposed iPiano algorithm, to solve the problem of descriptive supporting points efficiently.

Progressive Growing of GANs for Improved Quality, Stability, and Variation

A new training methodology for generative adversarial networks is described, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses, allowing for images of unprecedented quality.

Pluralistic Image Completion

This paper proposes a novel and probabilistically principled framework with two parallel paths for pluralistic image completion that utilizes the only one given ground truth to get prior distribution of missing parts and rebuild the original image from this distribution.

Missing Features Reconstruction Using a Wasserstein Generative Adversarial Imputation Network

Experiments show that GAIN and especially WGAIN are the best imputers regardless of the conditions and outperform or are comparative to MICE, k-NN, DAE, and VAEAC.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a