Image Inpainting for Irregular Holes Using Partial Convolutions

@inproceedings{Liu2018ImageIF,
  title={Image Inpainting for Irregular Holes Using Partial Convolutions},
  author={Guilin Liu and Fitsum A. Reda and Kevin J. Shih and Ting-Chun Wang and Andrew Tao and Bryan Catanzaro},
  booktitle={ECCV},
  year={2018}
}
Existing deep learning based image inpainting methods use a standard convolutional network over the corrupted image, using convolutional filter responses conditioned on both valid pixels as well as the substitute values in the masked holes (typically the mean value. [] Key Method We further include a mechanism to automatically generate an updated mask for the next layer as part of the forward pass. Our model outperforms other methods for irregular masks. We show qualitative and quantitative comparisons with…
Image Inpainting For Random Areas Using Dense Context Features
TLDR
Dense blocks for the U-Net architecture are introduced, which can alleviate the problem of gradient disappearance, while also reducing the number of parameters.
IMAGE INPAINTING FOR ARBITRARY HOLES USING CUSTUMIZED RESIDUAL BLOCK ARCHITECTURE WITH PARTIAL CONVOLUTIONS
TLDR
Qualitative and quantitative experimental demonstrate that the proposed Residual Partial Convolution network (RBPConv) can deal with the corrupted regions of arbitrary shapes and performs favorably against previous state-of-the-art methods.
Image Inpainting using Weighted Mask Convolution
TLDR
The weighted convolution that balances the valid and invalid pixels throughout the networks to help the network efficiently cope with various hole shapes is proposed and achieved improvements over the state-of-the-art inpainting methods.
Background Object Removal and Image Inpainting to Fill Irregular Holes
TLDR
This work aims to remove the background object from the image while ensuring that the regenerated image has minimal discrepancies, and makes use of partial convolution in which at every stage of the convolution network, it replaces the Convolution block with a partial convolved block.
Image Inpainting using Partial Convolution
TLDR
The aim of this project is to perform image inpainting using robust deep learning methods that use partial convolution layers that use Partial Convolution layers.
Image Inpainting Using AutoEncoder and Guided Selection of Predicted Pixels
TLDR
A network, similar to U-Net, is proposed for image inpainting that extracts various features from images, leading to better results, and improves the final results by replacing the damaged pixels with the recovered pixels of the output images.
Random-Shaped Image Inpainting using Dilated Convolution 642
TLDR
A new novel-based method is proposed for image inpainting of random-shaped missing regions with variable size and arbitrary locations across the image using dilated convolutions for composing multiscale context information without any loss in resolution as well as including a modification mask step after each convolution operation.
Image Inpainting with Onion Convolutions
TLDR
A novel approach to image inpainting problem is presented, which adapts exemplar-based methods for deep convolutional neural networks with the purpose of preserving feature continuities and semantic coherence with outperforms state-of-the-art methods.
Multidomain CT Metal Artifacts Reduction Using Partial Convolution Based Inpainting
TLDR
A multidomain method, which consists of both sinogram correction (projection domain step) and restored image correction (image-domain step), which achieves state-of-the-art (−75% MSE) improvement in comparison with a classic benchmark - Li-MAR.
Projection Inpainting Using Partial Convolution for Metal Artifact Reduction
TLDR
The experiments demonstrate that the U-Net with partial convolution is able to inpaint the metal corrupted areas better than that with conventional convolution.
...
...

References

SHOWING 1-10 OF 44 REFERENCES
Image Inpainting using Multi-Scale Feature Image Translation
TLDR
This work proposes a learning-based approach to generate visually coherent completion given a high-resolution image with missing components and shows that it not only generates results of comparable or better visual quality, but are orders of magnitude faster than previous state-of-the-art methods.
Semantic Image Inpainting with Perceptual and Contextual Losses
TLDR
A novel method for image inpainting based on a Deep Convolutional Generative Adversarial Network that can successfully predict semantic information in the missing region and achieve pixel-level photorealism, which is impossible by almost all existing methods.
Generative Image Inpainting with Contextual Attention
TLDR
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.
High-Resolution Image Inpainting Using Multi-scale Neural Patch Synthesis
TLDR
This work proposes a multi-scale neural patch synthesis approach based on joint optimization of image content and texture constraints, which not only preserves contextual structures but also produces high-frequency details by matching and adapting patches with the most similar mid-layer feature correlations of a deep classification network.
Semantic Image Inpainting with Deep Generative Models
TLDR
A novel method for semantic image inpainting, which generates the missing content by conditioning on the available data, and successfully predicts information in large missing regions and achieves pixel-level photorealism, significantly outperforming the state-of-the-art methods.
An Image Inpainting Technique Based on the Fast Marching Method
  • A. Telea
  • Computer Science
    J. Graphics, GPU, & Game Tools
  • 2004
TLDR
A new algorithm for digital inpainting based on the fast marching method for level set applications is presented, very simple to implement, fast, and produces nearly identical results to more complex, and usually slower, known methods.
Deep Image Prior
TLDR
It is shown that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, superresolution, and inpainting.
Generative Face Completion
TLDR
This paper demonstrates qualitatively and quantitatively that the proposed effective face completion algorithm is able to deal with a large area of missing pixels in arbitrary shapes and generate realistic face completion results.
Image inpainting
TLDR
A novel algorithm for digital inpainting of still images that attempts to replicate the basic techniques used by professional restorators, and does not require the user to specify where the novel information comes from.
Context Encoders: Feature Learning by Inpainting
TLDR
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.
...
...