TextGaze: Gaze-Controllable Face Generation with Natural Language

Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang

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.

Primary Subject Area: [Generation] Generative Multimedia

Secondary Subject Area: [Generation] Generative Multimedia

Relevance To Conference: Our work is related to multi-modal generation, with a focus on gaze-controllable face generation, and we introduce the first text-of-gaze dataset. Our model can control head and gaze behavior in face generation with natural language. Our research has potential applications in art, culture, and digital human generation. Given these aspects, we believe our research is highly relevant to the ACM MM conference.

Submission Number: 424