Generating a Fusion Image: One's Identity and Another's Shape

04/20/2018
by   Donggyu Joo, et al.
0

Generating a novel image by manipulating two input images is an interesting research problem in the study of generative adversarial networks (GANs). We propose a new GAN-based network that generates a fusion image with the identity of input image x and the shape of input image y. Our network can simultaneously train on more than two image datasets in an unsupervised manner. We define an identity loss LI to catch the identity of image x and a shape loss LS to get the shape of y. In addition, we propose a novel training method called Min-Patch training to focus the generator on crucial parts of an image, rather than its entirety. We show qualitative results on the VGG Youtube Pose dataset, Eye dataset (MPIIGaze and UnityEyes), and the Photo-Sketch-Cartoon dataset.

READ FULL TEXT

page 2

page 5

page 6

page 7

page 8

research
03/30/2021

Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition

Face photo-sketch synthesis and recognition has many applications in dig...
research
05/19/2018

Generative Creativity: Adversarial Learning for Bionic Design

Bionic design refers to an approach of generative creativity in which a ...
research
03/02/2020

VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images

We present a novel variational generative adversarial network (VGAN) bas...
research
04/11/2021

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

Solar cell electroluminescence (EL) defect segmentation is an interestin...
research
03/24/2019

SRGAN: Training Dataset Matters

Generative Adversarial Networks (GANs) in supervised settings can genera...
research
12/11/2017

Eye In-Painting with Exemplar Generative Adversarial Networks

This paper introduces a novel approach to in-painting where the identity...
research
11/02/2018

3D Pick & Mix: Object Part Blending in Joint Shape and Image Manifolds

We present 3D Pick & Mix, a new 3D shape retrieval system that provides ...

Please sign up or login with your details

Forgot password? Click here to reset