Rendering of Eyes for Eye-Shape Registration and Gaze Estimation
This addresses the data collection bottleneck for researchers and practitioners in computer vision working on eye-related tasks like gaze estimation, though it is incremental as it builds on existing computer graphics techniques.
The paper tackled the problem of time-consuming and unreliable manual annotation for eye image datasets in computer vision tasks by proposing a method to synthesize perfectly labeled photo-realistic training data quickly. The result was that their synthesized data outperformed state-of-the-art methods in eye-shape registration and cross-dataset gaze estimation.
Images of the eye are key in several computer vision problems, such as shape registration and gaze estimation. Recent large-scale supervised methods for these problems require time-consuming data collection and manual annotation, which can be unreliable. We propose synthesizing perfectly labelled photo-realistic training data in a fraction of the time. We used computer graphics techniques to build a collection of dynamic eye-region models from head scan geometry. These were randomly posed to synthesize close-up eye images for a wide range of head poses, gaze directions, and illumination conditions. We used our model's controllability to verify the importance of realistic illumination and shape variations in eye-region training data. Finally, we demonstrate the benefits of our synthesized training data (SynthesEyes) by out-performing state-of-the-art methods for eye-shape registration as well as cross-dataset appearance-based gaze estimation in the wild.