This record is in review state, the data has not yet been validated.
This is not the latest version of this item. The latest version can be found here.
Zero-Pair Image to Image Translation using Domain Conditional Normalization
Loading...
Author / Producer
Date
2021-01-01
Publication Type
Conference Paper
ETH Bibliography
Citations
Altmetric
Data
Rights / License
Abstract
In this paper, we propose an approach based on domain conditional normalization (DCN) for zero-pair image-to-image translation, i.e., translating between two domains which have no paired training data available but each have paired training data with a third domain. We employ a single generator which has an encoder-decoder structure and analyze different implementations of domain conditional normalization to obtain the desired target domain output. The validation benchmark uses RGB-depth pairs and RGB-semantic pairs for training and compares performance for the depth-semantic translation task. The proposed approaches improve in qualitative and quantitative terms over the compared methods, while using much fewer parameters. Code available at: https://github.com/samarthshukla/dcn
Permanent link
Publication status
External links
Editor
Book title
Journal / series
2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021
Volume
Pages / Article No.
3511 - 3518
Publisher
IEEE
Event
IEEE Winter Conference on Applications of Computer Vision (WACV)