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
Book ChapterDOI
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing
TL;DR: In this paper , a semantic-aligned scale-aware module is proposed to address the scale variation of moiré patterns, which outperforms state-of-the-art methods by a large margin while being much more lightweight.
Proceedings ArticleDOI
Preference-Based Image Generation
TL;DR: The Preference-Based Image Generation (PbIG), a new method to retrieve the corresponding latent code of the user’s mental image by adopting preference-based reinforcement learning, which learns from a user's judgment of the generated images by a pre-trained generative model.
Journal ArticleDOI
Dense-FCN: A Deep Learning Approach for Weather Radar Beam Blockage Correction
TL;DR: In this article , a fully convolutional neural network with dense connection is designed, and the multiclass cross entropy loss function is used to optimize the model, which achieved good performance in the evaluation indicators in the field of meteorology and image completion.
Journal ArticleDOI
Predictive World Models from Real-World Partial Observations
TL;DR: In this paper , a probabilistic predictive world model for real-world road environments is presented, which can predict a diverse set of fully observed plausible worlds from accumulated sensor observations.
Journal ArticleDOI
FingerGAN: A Constrained Fingerprint Generation Scheme for Latent Fingerprint Enhancement
TL;DR: A holistic framework is offered which can perform latent fingerprint enhancement in the context of directly optimizing minutia information, and demonstrates that this method outperforms the state of the arts performance significantly.
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.