New approach on Smiling faces with Domain Transfer in Latent Space

Sometimes we do not satisfy with our own old photo without smiling. Do you want to make it smile? One possible approach traditionally is to make use of the manipulation technique in latent space to achieve this. However, often we find that this may produce some errors. In this paper, we propose a new smile manipulation approach using Domain Transfer in Latent Space (DTLS) approach. We define various degrees of smile as a series of domains transfer in the DTLS. Results of the experimental work show that with this of our approach, manipulated photos show less errors compared with traditional methods, and the visual quality of our manipulated photos is good.

Authors

Publication Details

Published
2024-12-03
DOI
https://doi.org/10.1109/apsipaasc63619.2025.10848769
Citations
1
Primary Topic
Face recognition and analysis
Type
article
Field-Weighted Citation Impact
0.25

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

New approach on Smiling faces with Domain Transfer in Latent Space

Chun-Chuen Hui, Wan-Chi Siu, F. Duan
1 citations
Face recognition and analysis
0.25
article

New approach on Smiling faces with Domain Transfer in Latent Space

Chun-Chuen Hui, Wan-Chi Siu, F. Duan
article en
1 citations

Abstract

Sometimes we do not satisfy with our own old photo without smiling. Do you want to make it smile? One possible approach traditionally is to make use of the manipulation technique in latent space to achieve this. However, often we find that this may produce some errors. In this paper, we propose a new smile manipulation approach using Domain Transfer in Latent Space (DTLS) approach. We define various degrees of smile as a series of domains transfer in the DTLS. Results of the experimental work show that with this of our approach, manipulated photos show less errors compared with traditional methods, and the visual quality of our manipulated photos is good.

Saint Francis University, Hong Kong Polytechnic University
Openalex Percentile: Top 42%
Face recognition and analysis
0.25
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.