Published on Wed Sep 05 2018

A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation

Alexander H. Liu, Yen-Cheng Liu, Yu-Ying Yeh, Yu-Chiang Frank Wang

We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. The proposed network is able to perform continuous cross-domain image translation and manipulation.

0
0
0
Abstract

We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains. Realized by adversarial training with additional ability to exploit domain-specific information, the proposed network is able to perform continuous cross-domain image translation and manipulation, and produces desirable output images accordingly. In addition, the resulting feature representation exhibits superior performance of unsupervised domain adaptation, which also verifies the effectiveness of the proposed model in learning disentangled features for describing cross-domain data.

Wed Apr 03 2019
Computer Vision
Semantics-Aware Image to Image Translation and Domain Transfer
Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain. We present a new unsupervised image-to-image translation technique that leverages the underlying semantic information.
0
0
0
Thu May 24 2018
Computer Vision
Image-to-image translation for cross-domain disentanglement
Deep image translation methods have recently shown excellent results. We aim to separate the internal representation into three parts. The shared part contains information for both domains. The exclusive parts, on the other hand, contain factors of variation particular to each domain.
0
0
0
Tue Sep 17 2019
Computer Vision
Multi-mapping Image-to-Image Translation via Learning Disentanglement
Existing methods only consider one of the two aspects of image-to-image translation. We propose a novel unified model, which bridges these two objectives. Experiments demonstrate that our method outperforms state-of-the-art methods.
0
0
0
Sat Nov 02 2019
Computer Vision
Unsupervised Multi-Domain Multimodal Image-to-Image Translation with Explicit Domain-Constrained Disentanglement
Image-to-image translation aims to translate an image in one domain to a given reference image in another domain. Three main challenges remain in image-To-Image translation. We propose a unified framework for learning to generate diverse outputs using unpaired training data.
0
0
0
Tue Dec 10 2019
Computer Vision
Learning Domain Adaptive Features with Unlabeled Domain Bridges
Conventional cross-domain image-to-image translation methods assume that the source domain and target domain are closely related. This neglects a practical scenario where the domain discrepancy between the source and target is excessively large. We propose a novel approach to learn domain adaptive features between the largely-
0
0
0
Sun Nov 26 2017
Computer Vision
In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks
In unsupervised image-to-image translation, the goal is to learn the mapping between an input image and an output image. We show that leveraging multiple inputs generally improves the visual quality of the translated images.
0
0
0