Semantic Image Manipulation Using Scene Graphs (2020-04-07T00:00:00.000000Z)

TL;DR

This work introduces a spatio-semantic scene graph network that does not require direct supervision for constellation changes or image edits, and makes it possible to train the system from existing real-world datasets with no additional annotation effort.

Abstract

Image manipulation can be considered a special case of image generation where the image to be produced is a modification of an existing image. Image generation and manipulation have been, for the most part, tasks that operate on raw pixels. However, the remarkable progress in learning rich image and object representations has opened the way for tasks such as text-to-image or layout-to-image generation that are mainly driven by semantics. In our work, we address the novel problem of image manipulation from scene graphs, in which a user can edit images by merely applying changes in the nodes or edges of a semantic graph that is generated from the image. Our goal is to encode image information in a given constellation and from there on generate new constellations, such as replacing objects or even changing relationships between objects, while respecting the semantics and style from the original image. We introduce a spatio-semantic scene graph network that does not require direct supervision for constellation changes or image edits. This makes it possible to train the system from existing real-world datasets with no additional annotation effort.

Authors

N. Navab

26 papers

C. Rupprecht

8 papers

Gregory Hager

11 papers

TL;DR

Abstract

Authors

References63 items

Specifying Object Attributes and Relations in Interactive Scene Generation

Object-Driven Multi-Layer Scene Decomposition From a Single Image

Image Synthesis From Reconfigurable Layout and Style

Semantic Image Synthesis With Spatially-Adaptive Normalization

SC-FEGAN: Face Editing Generative Adversarial Network With User’s Sketch and Color

Spatial Fusion GAN for Image Synthesis

StoryGAN: A Sequential Conditional GAN for Story Visualization

Image Generation From Layout

Attentive Relational Networks for Mapping Images to Scene Graphs

3D-Aware Scene Manipulation via Inverse Graphics

Graph R-CNN for Scene Graph Generation

Compositional GAN: Learning Conditional Image Composition

Compositional GAN: Learning Image-Conditional Binary Composition

Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition

Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation

Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

Tensorize, Factorize and Regularize: Robust Visual Relationship Learning

Modular Generative Adversarial Networks

Image Generation from Scene Graphs

Guided Image Inpainting: Replacing an Image Region by Pulling Content From Another Image

Photographic Text-to-Image Synthesis with a Hierarchically-Nested Adversarial Network

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

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

StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation

Neural Motifs: Scene Graph Parsing with Global Context

Scene Graph Generation from Objects, Phrases and Region Captions

Photographic Image Synthesis with Cascaded Refinement Networks

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

Pixels to Graphs by Associative Embedding

Fader Networks: Manipulating Images by Sliding Attributes

Detecting Visual Relationships with Deep Relational Networks

Scene Graph Generation by Iterative Message Passing

CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

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

Image-to-Image Translation with Conditional Adversarial Networks

Conditional Image Synthesis with Auxiliary Classifier GANs

Neural Photo Editing with Introspective Adversarial Networks

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Generative Visual Manipulation on the Natural Image Manifold

Visual Relationship Detection with Language Priors

Semantic Image Inpainting with Deep Generative Models

Conditional Image Generation with PixelCNN Decoders

Improved Techniques for Training GANs

Generative Adversarial Text to Image Synthesis

Context Encoders: Feature Learning by Inpainting

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

Pixel Recurrent Neural Networks

Attribute2Image: Conditional Image Generation from Visual Attributes

DenseCap: Fully Convolutional Localization Networks for Dense Captioning

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Image retrieval using scene graphs

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Adam: A Method for Stochastic Optimization

Conditional Generative Adversarial Nets

Very Deep Convolutional Networks for Large-Scale Image Recognition

Auto-Encoding Variational Bayes

PatchNet

Recognition using visual phrases

Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

GENERATIVE ADVERSARIAL NETS

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names