EyeBAG: Accurate Control of Eye Blink and Gaze Based on Data Augmentation Leveraging Style Mixing
This work addresses eye control issues in face generation for applications like virtual avatars or media editing, representing an incremental improvement over existing methods.
The paper tackled the problem of poor eye control in generative face models by introducing a framework with separate modules for blink control and gaze redirection, using a novel data augmentation method based on style mixing, and demonstrated high-quality results with improved performance in downstream tasks.
Recent developments in generative models have enabled the generation of photo-realistic human face images, and downstream tasks utilizing face generation technology have advanced accordingly. However, models for downstream tasks are yet substandard at eye control (e.g. eye blink, gaze redirection). To overcome such eye control problems, we introduce a novel framework consisting of two distinct modules: a blink control module and a gaze redirection module. We also propose a novel data augmentation method to train each module, leveraging style mixing to obtain images with desired features. We show that our framework produces eye-controlled images of high quality, and demonstrate how it can be used to improve the performance of downstream tasks.