TextGaze: Gaze-Controllable Face Generation with Natural Language

TL;DR

This paper introduces TextGaze, a novel method for generating face images controllable by natural language descriptions of gaze and head pose, using a new dataset and diffusion models.

Contribution

It presents a new text-based gaze-controllable face generation task, a large dataset of gaze descriptions, and a diffusion-based method combining sketch and model-based modules.

Findings

Effective face generation from text descriptions of gaze.

Successful application on FFHQ dataset.

Availability of dataset and code for future research.

Abstract

Generating face image with specific gaze information has attracted considerable attention. Existing approaches typically input gaze values directly for face generation, which is unnatural and requires annotated gaze datasets for training, thereby limiting its application. In this paper, we present a novel gaze-controllable face generation task. Our approach inputs textual descriptions that describe human gaze and head behavior and generates corresponding face images. Our work first introduces a text-of-gaze dataset containing over 90k text descriptions spanning a dense distribution of gaze and head poses. We further propose a gaze-controllable text-to-face method. Our method contains a sketch-conditioned face diffusion module and a model-based sketch diffusion module. We define a face sketch based on facial landmarks and eye segmentation map. The face diffusion module generates face images from the face sketch, and the sketch diffusion module employs a 3D face model to generate face sketch from text description. Experiments on the FFHQ dataset show the effectiveness of our method. We will release our dataset and code for future research.