StarGAN v2: Diverse Image Synthesis for Multiple Domains (2019-12-04T00:00:00.000000Z)

TL;DR

StarGAN v2, a single framework that tackles image-to-image translation models with limited diversity and multiple models for all domains, is proposed and shows significantly improved results over the baselines.

Abstract

A good image-to-image translation model should learn a mapping between different visual domains while satisfying the following properties: 1) diversity of generated images and 2) scalability over multiple domains. Existing methods address either of the issues, having limited diversity or multiple models for all domains. We propose StarGAN v2, a single framework that tackles both and shows significantly improved results over the baselines. Experiments on CelebA-HQ and a new animal faces dataset (AFHQ) validate our superiority in terms of visual quality, diversity, and scalability. To better assess image-to-image translation models, we release AFHQ, high-quality animal faces with large inter- and intra-domain differences. The code, pretrained models, and dataset are available at https://github.com/clovaai/stargan-v2.

Authors

Yunjey Choi

2 papers

Youngjung Uh

3 papers

Jaejun Yoo

1 papers

TL;DR

Abstract

Authors

References58 items

Multi-mapping Image-to-Image Translation via Learning Disentanglement

SDIT: Scalable and Diverse Cross-domain Image Translation

Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss

Large Scale Adversarial Representation Learning

Coloring With Limited Data: Few-Shot Colorization via Memory Augmented Networks

Few-Shot Unsupervised Image-to-Image Translation

Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression

Semantic Image Synthesis With Spatially-Adaptive Normalization

Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

High-Fidelity Image Generation With Fewer Labels

MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation

Diversity-Sensitive Conditional Generative Adversarial Networks

Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation

A Style-Based Generator Architecture for Generative Adversarial Networks

SMIT: Stochastic Multi-Label Image-to-Image Translation

NSML: Meet the MLaaS platform with a real-world case study

Large Scale GAN Training for High Fidelity Natural Image Synthesis

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

Diverse Image-to-Image Translation via Disentangled Representations

Feature-wise transformations

The Unusual Effectiveness of Averaging in GAN Training

PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup

Exemplar Guided Unsupervised Image-to-Image Translation

Multimodal Unsupervised Image-to-Image Translation

Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data

cGANs with Projection Discriminator

Which Training Methods for GANs do actually Converge?

The Unreasonable Effectiveness of Deep Features as a Perceptual Metric

ComboGAN: Unrestrained Scalability for Image Domain Translation

NSML: A Machine Learning Platform That Enables You to Focus on Your Models

Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders

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

Toward Multimodal Image-to-Image Translation

Automatic differentiation in PyTorch

Progressive Growing of GANs for Improved Quality, Stability, and Variation

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

Improved Training of Wasserstein GANs

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

Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization

Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

Unsupervised Image-to-Image Translation Networks

Image-to-Image Translation with Conditional Adversarial Networks

Conditional Image Synthesis with Auxiliary Classifier GANs

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

Instance Normalization: The Missing Ingredient for Fast Stylization

Layer Normalization

Generative Adversarial Text to Image Synthesis

Identity Mappings in Deep Residual Networks

Rethinking the Inception Architecture for Computer Vision

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

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Adam: A Method for Stochastic Optimization

Conditional Generative Adversarial Nets

ImageNet classification with deep convolutional neural networks

Et al

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

Rectifier Nonlinearities Improve Neural Network Acoustic Models

and as an in

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names