Semantic Image Inpainting with Deep Generative Models
Raymond A. Yeh,Chen Chen,Teck Yian Lim,Alexander G. Schwing,Alexander G. Schwing,Mark Hasegawa-Johnson,Minh N. Do +6 more
- pp 6882-6890
Reads0
Chats0
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.Abstract:
Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results due to the lack of high level context. In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data. Given a trained generative model, we search for the closest encoding of the corrupted image in the latent image manifold using our context and prior losses. This encoding is then passed through the generative model to infer the missing content. In our method, inference is possible irrespective of how the missing content is structured, while the state-of-the-art learning based method requires specific information about the holes in the training phase. Experiments on three datasets show that our method successfully predicts information in large missing regions and achieves pixel-level photorealism, significantly outperforming the state-of-the-art methods.read more
Citations
More filters
Proceedings ArticleDOI
An Approach for Objective Quality Assessment of Image Inpainting Results
Dylan Seychell,Carl J. Debono +1 more
TL;DR: This work demonstrates how traditional in-painting techniques can be objectively evaluated and compared together with modern deep learning and adversarial approaches and further demonstrates how an unsupervised technique compares better than deep learning approaches.
3D Human Face Reconstruction and 2D Appearance Synthesis
TL;DR: This dissertation proposes three image-based face reconstruction approaches according to different assumption of inputs and proposes a deep neutral network to solve the HMD removal problem considering it as a face inpainting problem and explores the applicability of these reconstructions on four interesting applications.
Posted Content
Facial Information Recovery from Heavily Damaged Images using Generative Adversarial Network- PART 1.
TL;DR: This article proposes a kernel free framework based on conditional-GAN to recover the information from the heavily damaged images and generated images show that the network has the potential to recovered the probable information of blurred images from the learned features.
Patent
A face image restoration method and device based on VAE-GAN and similar block search
TL;DR: Zhang et al. as mentioned in this paper proposed a VAE-GAN based face image restoration method and device based on similar block search, which mainly comprises the steps that (1) using a face image library sample to train a constructed VAEGAN network model to optimize parameters of a generator G and a discriminator D in the model; (2) inputting a to-berestored image into the trained generator G to generate a blurred image M with semantic information in a to be-restored area; (3) searching a similar block Z from the image of the face
Book ChapterDOI
Pushing the Limits of Exoplanet Discovery via Direct Imaging with Deep Learning
Kai Hou Yip,Nikolaos Nikolaou,Piero Coronica,Angelos Tsiaras,Billy Edwards,Quentin Changeat,Mario Morvan,Beth Biller,Sasha Hinkley,Jeffrey Salmond,Matthew Archer,Paul Sumption,Elodie Choquet,Rémi Soummer,Laurent Pueyo,Ingo Waldmann +15 more
TL;DR: In this paper, a Generative Adversarial Network (GAN) was used to obtain a suitable dataset for training Convolutional Neural Network classifiers to detect and locate planets across a wide range of SNRs.
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.
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.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Journal Article
Visualizing Data using t-SNE
TL;DR: A new technique called t-SNE that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map, a variation of Stochastic Neighbor Embedding that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.