RAIN: robust and adaptive image manipulation based on GAN inversion with a text condition

Haoyu Cai; Longshan Shang; Lei Gong; Chao Wang

doi:10.1117/12.2678914

8 May 2023 RAIN: robust and adaptive image manipulation based on GAN inversion with a text condition

Haoyu Cai , Longshan Shang, Lei Gong , Chao Wang

Proceedings Volume 12635, Second International Conference on Algorithms, Microchips, and Network Applications (AMNA 2023); 126351D (2023) https://doi.org/10.1117/12.2678914
Event: International Conference on Algorithms, Microchips, and Network Applications 2023, 2023, Zhengzhou, China

Abstract

Recent work has shown various interesting semantic image manipulation methods based on GAN guided by text descriptions. A method based on GAN inversion can achieve versatile image manipulation functions without a time-consuming preprocessing stage. However, the method suffers from a lack of self-adaptation due to the intrinsic conflict between multi-objective losses. Meanwhile, the method applied in image manipulation guided by text conditions is not robust due to the vast and ambiguous search space. To solve the above problems, we propose a novel framework RAIN based on GAN inversion, which can achieve robust and adaptive text-driven image manipulation. As shown in Fig. 1(c), RAIN contains two main parts: CEV Initialization and RAGAN inversion. CEV Initialization can adaptively provide a Candidate Editing Vector (CEV) in a short time. RGAN inversion is a multi-stage optimization scheme utilizing the CEV as prior knowledge to prune search space. In RAGAN inversion, we explore how to improve the vision-language model's perception capability to restrict search space further. The objective of the paper is guaranteeing semantic correctness and image quality in a time-constrained scenario compared to the SOTA image manipulation methods guided by text descriptions. Extensive experiments show that RAIN can manipulate images guided by text description while meeting robustness and self-adaptation.

Citation Download Citation

Haoyu Cai , Longshan Shang, Lei Gong , and Chao Wang "RAIN: robust and adaptive image manipulation based on GAN inversion with a text condition", Proc. SPIE 12635, Second International Conference on Algorithms, Microchips, and Network Applications (AMNA 2023), 126351D (8 May 2023); https://doi.org/10.1117/12.2678914

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Gallium nitride

Rain

Semantics

Image quality

Image segmentation

Education and training

Visual process modeling

Show All Keywords

Keywords/Phrases

Search In:

Publication Years