The GAN that Warped: Semantic Attribute Editing with Unpaired Data

11/30/2018
by   Garoe Dorta, et al.
12

Deep neural networks have recently been used to edit images with great success. However, they are often limited by only being able to work at a restricted range of resolutions. They are also so flexible that semantic face edits can often result in an unwanted loss of identity. This work proposes a model that learns how to perform semantic image edits through the application of smooth warp fields. This warp field can be efficiently predicted at a reasonably low resolution and then resampled and applied at arbitrary resolutions. Previous approaches that attempted to use warping for semantic edits required paired data, that is example images of the same object with different semantic characteristics. In contrast, we employ recent advances in Generative Adversarial Networks that allow our model to be effectively trained with unpaired data. We demonstrate the efficacy of our method for editing face images at very high resolutions (4k images) with an efficient single forward pass of a deep network at a lower resolution. We illustrate how the extent of our edits can be trivially reduced or exaggerated by scaling the predicted warp field, and we also show that our edits are substantially better at maintaining the subject's identity.

READ FULL TEXT

page 1

page 7

page 11

page 13

page 14

page 15

page 16

page 20

research
05/16/2019

FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network

There are many factors affecting visual face recognition, such as low re...
research
11/22/2022

S^2-Flow: Joint Semantic and Style Editing of Facial Images

The high-quality images yielded by generative adversarial networks (GANs...
research
08/11/2023

Zero-shot Text-driven Physically Interpretable Face Editing

This paper proposes a novel and physically interpretable method for face...
research
11/17/2021

SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency

Semantically guided conditional Generative Adversarial Networks (cGANs) ...
research
08/26/2018

Twin-GAN -- Unpaired Cross-Domain Image Translation with Weight-Sharing GANs

We present a framework for translating unlabeled images from one domain ...
research
08/03/2023

Lode Enhancer: Level Co-creation Through Scaling

We explore AI-powered upscaling as a design assistance tool in the conte...
research
06/06/2023

A Unified Framework to Super-Resolve Face Images of Varied Low Resolutions

The existing face image super-resolution (FSR) algorithms usually train ...

Please sign up or login with your details

Forgot password? Click here to reset