CrossGaze: A Strong Method for 3D Gaze Estimation in the Wild
This work addresses gaze estimation for applications like human-computer interaction and virtual reality, but it is incremental as it builds on established models without introducing a new paradigm.
The authors tackled 3D gaze estimation in unconstrained environments by proposing CrossGaze, a method that leverages existing computer vision models and attention modules, achieving a mean angular error of 9.94 degrees on the Gaze360 benchmark.
Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality. Estimating the direction of looking in unconstrained environments is difficult, due to the many factors that can obscure the face and eye regions. In this work we propose CrossGaze, a strong baseline for gaze estimation, that leverages recent developments in computer vision architectures and attention-based modules. Unlike previous approaches, our method does not require a specialised architecture, utilizing already established models that we integrate in our architecture and adapt for the task of 3D gaze estimation. This approach allows for seamless updates to the architecture as any module can be replaced with more powerful feature extractors. On the Gaze360 benchmark, our model surpasses several state-of-the-art methods, achieving a mean angular error of 9.94 degrees. Our proposed model serves as a strong foundation for future research and development in gaze estimation, paving the way for practical and accurate gaze prediction in real-world scenarios.