TextGaze: Gaze-Controllable Face Generation with Natural Language
This addresses the limitation of unnatural input and reliance on annotated gaze datasets for face generation applications, though it is incremental as it builds on existing text-to-image and face generation methods.
The paper tackles the problem of generating face images with specific gaze information by introducing a gaze-controllable face generation task that uses natural language descriptions instead of direct gaze values, and it demonstrates effectiveness on the FFHQ dataset with a new dataset of over 90k text descriptions.
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.