Semantic Image Synthesis With Spatially-Adaptive Normalization
Taesung Park,Ming-Yu Liu,Ting-Chun Wang,Jun-Yan Zhu +3 more
- pp 2337-2346
Reads0
Chats0
TLDR
S spatially-adaptive normalization is proposed, a simple but effective layer for synthesizing photorealistic images given an input semantic layout that allows users to easily control the style and content of image synthesis results as well as create multi-modal results.Abstract:
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the network, forcing the network to memorize the information throughout all the layers. Instead, we propose using the input layout for modulating the activations in normalization layers through a spatially-adaptive, learned affine transformation. Experiments on several challenging datasets demonstrate the superiority of our method compared to existing approaches, regarding both visual fidelity and alignment with input layouts. Finally, our model allows users to easily control the style and content of image synthesis results as well as create multi-modal results. Code is available upon publication.read more
Citations
More filters
Proceedings ArticleDOI
Data Augmentation Using GANs for Crop/Weed Segmentation in Precision Farming
Mulham Fawakherji,Ciro Potena,Ibis Prevedello,Alberto Pretto,Domenico Daniele Bloisi,Daniele Nardi +5 more
TL;DR: This work tackles the crop/weed segmentation problem by using a synthetic image generation method to augment the training dataset without the need of manually labelling the images, and shows that the method well generalizes across multiple architectures.
Book ChapterDOI
Controllable Image Synthesis via SegVAE
TL;DR: In this paper, SegVAE is proposed to synthesize semantic maps in an iterative manner using conditional variational autoencoder and image-to-image translation model.
Posted Content
Exoskeleton-covered soft finger with vision-based proprioception and tactile sensing
TL;DR: This work describes the development of a vision-based proprioceptive and tactile sensor for soft robots called GelFlex, which is inspired by previous GelSight sensing techniques and develops a novel exoskeleton-covered soft finger with embedded cameras and deep learning methods that enable high-resolution proprioception sensing and rich tactile sensing.
Journal ArticleDOI
A review of design intelligence: progress, problems, and challenges
TL;DR: The current emerging framework of design intelligence is summarized and the state-of-the-art techniques of related topics, including user needs analysis, ideation, content generation, and design evaluation are reviewed.
Proceedings ArticleDOI
BlobGAN: Spatially Disentangled Scene Representations
TL;DR: An unsupervised, mid-level representation for a generative model of scenes that allows effortless rearrangement, removal, cloning, and restyling of objects in scenes and measures correlation between blob presence and semantic categories as predicted by an off-the-shelf network to empirically verify the associations discovered by the model.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
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
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
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.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.