Corpus ID: 1840346

LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation

@article{Yang2017LRGANLR,
  title={LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation},
  author={Jianwei Yang and A. Kannan and Dhruv Batra and Devi Parikh},
  journal={ArXiv},
  year={2017},
  volume={abs/1703.01560}
}
We present LR-GAN: an adversarial image generation model which takes scene structure and context into account. Unlike previous generative adversarial networks (GANs), the proposed GAN learns to generate image background and foregrounds separately and recursively, and stitch the foregrounds on the background in a contextually relevant manner to produce a complete natural image. For each foreground, the model learns to generate its appearance, shape and pose. The whole model is unsupervised, and… Expand

Paper Mentions

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
TLDR
Extensive experiments demonstrate that the proposed stacked generative adversarial networks significantly outperform other state-of-the-art methods in generating photo-realistic images. Expand
SpatialGAN: Progressive Image Generation Based on Spatial Recursive Adversarial Expansion
TLDR
The quality of imagesgenerated by SpatialGAN is better than that of images generated by GANs without cascading and comparative with the state of art methods with cascading. Expand
Consistent Embedded GAN for Image-to-Image Translation
TLDR
Unlike existing GANs models that their discriminators attempt to differentiate between real images from the dataset and fake samples produced by the generator, the discriminator in this model distinguishes the real images and fake images in the latent space to alleviate the impact of the redundancy and noise in generated images. Expand
How Generative Adversarial Nets and its variants Work: An Overview of GAN
TLDR
Details of GAN are looked into that firstly show how it operates and fundamental meaning of objective functions and point to GAN variants applied to vast amount of tasks. Expand
Compositional GAN: Learning Conditional Image Composition
TLDR
This work proposes to model object composition in a GAN framework as a self-consistent composition-decomposition network and reveals that the learned model captures potential interactions between the two object domains given as input to output new instances of composed scene at test time in a reasonable fashion. Expand
ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing
TLDR
This work exploits an iterative STN warping scheme and proposes a sequential training strategy that achieves better results compared to naive training of a single generator, which it calls Spatial Transformer GANs (ST-GANs). Expand
Compositional GAN: Learning Image-Conditional Binary Composition
TLDR
This work proposes a novel self-consistent Composition-by-Decomposition network to compose a pair of objects and indicates that the learned model captures potential interactions between the two object domains, and generates realistic composed scenes at test time. Expand
Decomposing Image Generation into Layout Prediction and Conditional Synthesis
TLDR
This article investigates splitting the optimisation of generative adversarial networks into two parts, by first generating a semantic segmentation masks from noise and then translating that segmentation mask into an image. Expand
3 C-GAN : A N CONDITION-CONTEXT-COMPOSITE GENERATIVE ADVERSARIAL NETWORKS FOR GENERATING IMAGES SEPARATELY
We present 3C-GAN: a novel multiple generators structures, that contains one conditional generator that generates a semantic part of an image conditional on its input label, and one context generatorExpand
Stacked Generative Adversarial Networks
TLDR
A novel generative model named Stacked Generative Adversarial Networks (SGAN), which is trained to invert the hierarchical representations of a bottom-up discriminative network, which is able to generate images of much higher quality than GANs without stacking. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 36 REFERENCES
Generating Images Part by Part with Composite Generative Adversarial Networks
TLDR
A model called composite generative adversarial network is proposed, that reveals the complex structure of images with multiple generators in which each generator generates some part of the image to create a new single image. Expand
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
TLDR
A generative parametric model capable of producing high quality samples of natural images using a cascade of convolutional networks within a Laplacian pyramid framework to generate images in a coarse-to-fine fashion. Expand
Generative Image Modeling Using Style and Structure Adversarial Networks
TLDR
This paper factorize the image generation process and proposes Style and Structure Generative Adversarial Network, a model that is interpretable, generates more realistic images and can be used to learn unsupervised RGBD representations. Expand
Generative Adversarial Text to Image Synthesis
TLDR
A novel deep architecture and GAN formulation is developed to effectively bridge advances in text and image modeling, translating visual concepts from characters to pixels. Expand
Generating images with recurrent adversarial networks
TLDR
This work proposes a recurrent generative model that can be trained using adversarial training to generate very good image samples, and proposes a way to quantitatively compare adversarial networks by having the generators and discriminators of these networks compete against each other. Expand
Learning What and Where to Draw
TLDR
This work proposes a new model, the Generative Adversarial What-Where Network (GAWWN), that synthesizes images given instructions describing what content to draw in which location, and shows high-quality 128 x 128 image synthesis on the Caltech-UCSD Birds dataset. Expand
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes. Expand
Energy-based Generative Adversarial Network
We introduce the "Energy-based Generative Adversarial Network" model (EBGAN) which views the discriminator as an energy function that attributes low energies to the regions near the data manifold andExpand
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
TLDR
This work introduces a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain architectural constraints, and demonstrates that they are a strong candidate for unsupervised learning. Expand
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand
...
1
2
3
4
...