Guided Image-to-Image Translation With Bi-Directional Feature Transformation

We address the problem of guided image-to-image translation where we translate an input image into another while respecting the constraints provided by an external, user-provided guidance image. Various types of conditioning mechanisms for leveraging the given guidance image have been explored, incl...

Full description

Saved in:
Bibliographic Details
Main Authors: Albahar, Badour, Huang, Jia-Bin
Format: Conference Proceeding
Language:English
Subjects:
Bidirectional control
Gallium nitride
Generators
Image color analysis
Image generation
Task analysis
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We address the problem of guided image-to-image translation where we translate an input image into another while respecting the constraints provided by an external, user-provided guidance image. Various types of conditioning mechanisms for leveraging the given guidance image have been explored, including input concatenation, feature concatenation, and conditional affine transformation of feature activations. All these conditioning mechanisms, however, are uni-directional, i.e., no information flow from the input image back to the guidance. To better utilize the constraints of the guidance image, we present a bi-directional feature transformation (bFT) scheme. We show that our novel bFT scheme outperforms other conditioning schemes and has comparable results to state-of-the-art methods on different tasks.
ISSN:2380-7504
DOI:10.1109/ICCV.2019.00911