Specifying Object Attributes and Relations in Interactive Scene Generation (2019-09-11T00:00:00.000000Z)

TL;DR

The method separates between a layout embedding and an appearance embedding, which leads to generated images that better match the scene graph, have higher visual quality, and support more complex scene graphs.

Abstract

We introduce a method for the generation of images from an input scene graph. The method separates between a layout embedding and an appearance embedding. The dual embedding leads to generated images that better match the scene graph, have higher visual quality, and support more complex scene graphs. In addition, the embedding scheme supports multiple and diverse output images per scene graph, which can be further controlled by the user. We demonstrate two modes of per-object control: (i) importing elements from other images, and (ii) navigation in the object space by selecting an appearance archetype. Our code is publicly available at https://www.github.com/ashual/scene_generation.

Authors

Lior Wolf

7 papers

Oron Ashual

2 papers

TL;DR

Abstract

Authors

References31 items

Image Generation From Layout

GAN Dissection: Visualizing and Understanding Generative Adversarial Networks

Image Generation from Scene Graphs

Multiple Source Domain Adaptation with Adversarial Learning

Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Semantic Image Retrieval via Active Grounding of Visual Situations

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

COCO-Stuff: Thing and Stuff Classes in Context

StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks

Image-to-Image Translation with Conditional Adversarial Networks

Least Squares Generative Adversarial Networks

Instance Normalization: The Missing Ingredient for Fast Stylization

Improved Techniques for Training GANs

Generative Adversarial Text to Image Synthesis

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

Deep Residual Learning for Image Recognition

Image retrieval using scene graphs

Adam: A Method for Stochastic Optimization

Conditional Generative Adversarial Nets

Going deeper with convolutions

Very Deep Convolutional Networks for Large-Scale Image Recognition

ImageNet classification with deep convolutional neural networks

Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

Vision: A computational investigation into the human representation and processing of visual information: David Marr. San Francisco: W. H. Freeman, 1982. pp. xvi + 397

Adversarial Networks

GENERATIVE ADVERSARIAL NETS

The Graph Neural Network Model

Visualizing Data using t-SNE

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names