# Pose-variant 3D Facial Attribute Generation

## TL;DR

This paper introduces a GAN-based framework for generating facial attributes directly on 3D face representations from a single image, achieving photorealistic and identity-preserving results in unconstrained poses.

## Contribution

It proposes a novel 3D attribute generation method using UV maps with two GAN components, improving realism and identity preservation over prior 2D approaches.

## Key findings

- Outperforms prior methods in attribute generation accuracy
- Produces more photorealistic and geometrically consistent images
- Maintains face identity effectively

## Abstract

We address the challenging problem of generating facial attributes using a single image in an unconstrained pose. In contrast to prior works that largely consider generation on 2D near-frontal images, we propose a GAN-based framework to generate attributes directly on a dense 3D representation given by UV texture and position maps, resulting in photorealistic, geometrically-consistent and identity-preserving outputs. Starting from a self-occluded UV texture map obtained by applying an off-the-shelf 3D reconstruction method, we propose two novel components. First, a texture completion generative adversarial network (TC-GAN) completes the partial UV texture map. Second, a 3D attribute generation GAN (3DA-GAN) synthesizes the target attribute while obtaining an appearance consistent with 3D face geometry and preserving identity. Extensive experiments on CelebA, LFW and IJB-A show that our method achieves consistently better attribute generation accuracy than prior methods, a higher degree of qualitative photorealism and preserves face identity information.