Open AccessPosted Content
Image Inpainting for Irregular Holes Using Partial Convolutions
Reads0
Chats0
TLDR
In this paper, the convolution is masked and renormalized to be conditioned on only valid pixels, and a mechanism is proposed to automatically generate an updated mask for the next layer as part of the forward pass.Abstract:
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). This often leads to artifacts such as color discrepancy and blurriness. Post-processing is usually used to reduce such artifacts, but are expensive and may fail. We propose the use of partial convolutions, where the convolution is masked and renormalized to be conditioned on only valid pixels. 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 other methods to validate our approach.read more
Citations
More filters
Proceedings Article
Implicit Neural Representations with Periodic Activation Functions
TL;DR: In this paper, the authors propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or Sirens, are ideally suited for representing complex natural signals and their derivatives.
Posted Content
Free-Form Image Inpainting with Gated Convolution
TL;DR: The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers.
Posted Content
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
TL;DR: A new approach for image inpainting that does a better job of reproducing filled regions exhibiting fine details is developed and outperforms current state-of-the-art techniques quantitatively and qualitatively.
Proceedings ArticleDOI
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction
TL;DR: This work proposes a two-stage model that separates the inpainting problem into structure prediction and image completion, similar to sketch art, and demonstrates that this approach outperforms current state-of-the-art techniques quantitatively and qualitatively.
Proceedings ArticleDOI
Foreground-Aware Image Inpainting
TL;DR: Zhang et al. as discussed by the authors propose a foreground-aware image inpainting system that explicitly disentangles structure inference and content completion to predict the foreground contour first, and then inpaints the missing region using the predicted contour as guidance.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Book ChapterDOI
U-Net: Convolutional Networks for Biomedical Image Segmentation
TL;DR: Neber et al. as discussed by the authors proposed a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently, which can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.
Journal ArticleDOI
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.