Learning to hallucinate face images via component generation and enhancement

We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures...

Full description

Saved in:
Bibliographic Details
Main Authors: SONG, Yibing, ZHANG, Jiawei, HE, Shengfeng, BAO, Linchao, YANG, Qingxiong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2017
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8429
https://ink.library.smu.edu.sg/context/sis_research/article/9432/viewcontent/0633.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-9432
record_format dspace
spelling sg-smu-ink.sis_research-94322024-01-04T10:07:15Z Learning to hallucinate face images via component generation and enhancement SONG, Yibing ZHANG, Jiawei HE, Shengfeng BAO, Linchao YANG, Qingxiong We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods. 2017-08-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8429 info:doi/10.24963/ijcai.2017/633 https://ink.library.smu.edu.sg/context/sis_research/article/9432/viewcontent/0633.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 Artificial intelligence Tunneling (excavation) Artificial Intelligence and Robotics Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Artificial intelligence
Tunneling (excavation)
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
spellingShingle Artificial intelligence
Tunneling (excavation)
Artificial Intelligence and Robotics
Graphics and Human Computer Interfaces
SONG, Yibing
ZHANG, Jiawei
HE, Shengfeng
BAO, Linchao
YANG, Qingxiong
Learning to hallucinate face images via component generation and enhancement
description We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods.
format text
author SONG, Yibing
ZHANG, Jiawei
HE, Shengfeng
BAO, Linchao
YANG, Qingxiong
author_facet SONG, Yibing
ZHANG, Jiawei
HE, Shengfeng
BAO, Linchao
YANG, Qingxiong
author_sort SONG, Yibing
title Learning to hallucinate face images via component generation and enhancement
title_short Learning to hallucinate face images via component generation and enhancement
title_full Learning to hallucinate face images via component generation and enhancement
title_fullStr Learning to hallucinate face images via component generation and enhancement
title_full_unstemmed Learning to hallucinate face images via component generation and enhancement
title_sort learning to hallucinate face images via component generation and enhancement
publisher Institutional Knowledge at Singapore Management University
publishDate 2017
url https://ink.library.smu.edu.sg/sis_research/8429
https://ink.library.smu.edu.sg/context/sis_research/article/9432/viewcontent/0633.pdf
_version_ 1787590747983183872