Efficient 3D-Aware Facial Image Editing via Attribute-Specific Prompt Learning

TL;DR

This paper introduces a scalable, text-guided 3D-aware facial image editing framework that uses attribute-specific prompt learning to control facial attributes across various poses, ensuring view consistency and identity preservation.

Contribution

It proposes a novel, plug-and-play, text-driven style token-based latent attribute editor (LAE) that enables scalable, attribute-specific editing in 3D-aware GANs using a pre-trained vision-language model.

Findings

High-quality, view-consistent facial image editing across multiple attributes.

Effective attribute control using text-guided prompts in 3D-aware face generation.

Scalable approach avoiding separate models for each attribute.

Abstract

Drawing upon StyleGAN's expressivity and disentangled latent space, existing 2D approaches employ textual prompting to edit facial images with different attributes. In contrast, 3D-aware approaches that generate faces at different target poses require attribute-specific classifiers, learning separate model weights for each attribute, and are not scalable for novel attributes. In this work, we propose an efficient, plug-and-play, 3D-aware face editing framework based on attribute-specific prompt learning, enabling the generation of facial images with controllable attributes across various target poses. To this end, we introduce a text-driven learnable style token-based latent attribute editor (LAE). The LAE harnesses a pre-trained vision-language model to find text-guided attribute-specific editing direction in the latent space of any pre-trained 3D-aware GAN. It utilizes learnable style tokens and style mappers to learn and transform this editing direction to 3D latent space. To train LAE with multiple attributes, we use directional contrastive loss and style token loss. Furthermore, to ensure view consistency and identity preservation across different poses and attributes, we employ several 3D-aware identity and pose preservation losses. Our experiments show that our proposed framework generates high-quality images with 3D awareness and view consistency while maintaining attribute-specific features. We demonstrate the effectiveness of our method on different facial attributes, including hair color and style, expression, and others.