Pose guided person image generation

This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG^2 utilizes the pose information explicitly and consists of two key stages: pose inte...

Full description

Saved in:
Bibliographic Details
Main Authors: MA, Liqian, JIA, Xu, SUN, Qianru, SCHIELE, Bernt, TUYTELAARS, Tinne, VAN GOOL, Luc
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2017
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4458
https://ink.library.smu.edu.sg/context/sis_research/article/5461/viewcontent/6644_pose_guided_person_image_generation.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5461
record_format dspace
spelling sg-smu-ink.sis_research-54612021-02-19T02:13:30Z Pose guided person image generation MA, Liqian JIA, Xu SUN, Qianru SCHIELE, Bernt TUYTELAARS, Tinne VAN GOOL, Luc This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG^2 utilizes the pose information explicitly and consists of two key stages: pose integration and image refinement. In the first stage the condition image and the target pose are fed into a U-Net-like network to generate an initial but coarse image of the person with the target pose. The second stage then refines the initial and blurry result by training a U-Net-like generator in an adversarial way. Extensive experimental results on both 128x64 re-identification images and 256x256 fashion photos show that our model generates high-quality person images with convincing details. 2017-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4458 https://ink.library.smu.edu.sg/context/sis_research/article/5461/viewcontent/6644_pose_guided_person_image_generation.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Person image generation pose estimation generative adversarial networks Artificial Intelligence and Robotics Computer Sciences Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Person image generation
pose estimation
generative adversarial networks
Artificial Intelligence and Robotics
Computer Sciences
Numerical Analysis and Scientific Computing
spellingShingle Person image generation
pose estimation
generative adversarial networks
Artificial Intelligence and Robotics
Computer Sciences
Numerical Analysis and Scientific Computing
MA, Liqian
JIA, Xu
SUN, Qianru
SCHIELE, Bernt
TUYTELAARS, Tinne
VAN GOOL, Luc
Pose guided person image generation
description This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG^2 utilizes the pose information explicitly and consists of two key stages: pose integration and image refinement. In the first stage the condition image and the target pose are fed into a U-Net-like network to generate an initial but coarse image of the person with the target pose. The second stage then refines the initial and blurry result by training a U-Net-like generator in an adversarial way. Extensive experimental results on both 128x64 re-identification images and 256x256 fashion photos show that our model generates high-quality person images with convincing details.
format text
author MA, Liqian
JIA, Xu
SUN, Qianru
SCHIELE, Bernt
TUYTELAARS, Tinne
VAN GOOL, Luc
author_facet MA, Liqian
JIA, Xu
SUN, Qianru
SCHIELE, Bernt
TUYTELAARS, Tinne
VAN GOOL, Luc
author_sort MA, Liqian
title Pose guided person image generation
title_short Pose guided person image generation
title_full Pose guided person image generation
title_fullStr Pose guided person image generation
title_full_unstemmed Pose guided person image generation
title_sort pose guided person image generation
publisher Institutional Knowledge at Singapore Management University
publishDate 2017
url https://ink.library.smu.edu.sg/sis_research/4458
https://ink.library.smu.edu.sg/context/sis_research/article/5461/viewcontent/6644_pose_guided_person_image_generation.pdf
_version_ 1770574844970139648