PrefGen: Preference Guided Image Generation with Relative Attributes

by   Alec Helbling, et al.

Deep generative models have the capacity to render high fidelity images of content like human faces. Recently, there has been substantial progress in conditionally generating images with specific quantitative attributes, like the emotion conveyed by one's face. These methods typically require a user to explicitly quantify the desired intensity of a visual attribute. A limitation of this method is that many attributes, like how "angry" a human face looks, are difficult for a user to precisely quantify. However, a user would be able to reliably say which of two faces seems "angrier". Following this premise, we develop the PrefGen system, which allows users to control the relative attributes of generated images by presenting them with simple paired comparison queries of the form "do you prefer image a or image b?" Using information from a sequence of query responses, we can estimate user preferences over a set of image attributes and perform preference-guided image editing and generation. Furthermore, to make preference localization feasible and efficient, we apply an active query selection strategy. We demonstrate the success of this approach using a StyleGAN2 generator on the task of human face editing. Additionally, we demonstrate how our approach can be combined with CLIP, allowing a user to edit the relative intensity of attributes specified by text prompts. Code at


page 1

page 2

page 4

page 5

page 14

page 15


Oracle Guided Image Synthesis with Relative Queries

Isolating and controlling specific features in the outputs of generative...

GAN-Control: Explicitly Controllable GANs

We present a framework for training GANs with explicit control over gene...

On the Biometric Capacity of Generative Face Models

There has been tremendous progress in generating realistic faces with hi...

MyStyle++: A Controllable Personalized Generative Prior

In this paper, we propose an approach to obtain a personalized generativ...

FaceController: Controllable Attribute Editing for Face in the Wild

Face attribute editing aims to generate faces with one or multiple desir...

Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning

In recent years, image generation has made great strides in improving th...

Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach

Manipulating visual attributes of images through human-written text is a...

Please sign up or login with your details

Forgot password? Click here to reset