Interactive Optimization of Generative Image Modelling using Sequential Subspace Search and Content‐based Guidance
Loading...
Date
2021
Journal Title
Journal ISSN
Volume Title
Publisher
© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd
Abstract
Generative image modeling techniques such as GAN demonstrate highly convincing image generation result. However, user interaction is often necessary to obtain desired results. Existing attempts add interactivity but require either tailored architectures or extra data. We present a human‐in‐the‐optimization method that allows users to directly explore and search the latent vector space of generative image modelling. Our system provides multiple candidates by sampling the latent vector space, and the user selects the best blending weights within the subspace using multiple sliders. In addition, the user can express their intention through image editing tools. The system samples latent vectors based on inputs and presents new candidates to the user iteratively. An advantage of our formulation is that one can apply our method to arbitrary pre‐trained model without developing specialized architecture or data. We demonstrate our method with various generative image modelling applications, and show superior performance in a comparative user study with prior art iGAN [ZKSE16].
Description
@article{10.1111:cgf.14188,
journal = {Computer Graphics Forum},
title = {{Interactive Optimization of Generative Image Modelling using Sequential Subspace Search and Content‐based Guidance}},
author = {Chong, Toby and Shen, I‐Chao and Sato, Issei and Igarashi, Takeo},
year = {2021},
publisher = {© 2021 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd},
ISSN = {1467-8659},
DOI = {10.1111/cgf.14188}
}