HOIGaze: Gaze Estimation During Hand-Object Interactions in Extended Reality Exploiting Eye-Hand-Head Coordination

twin (ADT) datasets and show that it significantly outperforms state-of-theart methods, achieving an average improvement of 15.6% on HOT3D and 6.0% on ADT in mean angular error.To demonstrate the potential of our method, we further report significant performance improvements for the sample downstream task of eye-based activity recognition on ADT.Taken together, our results underline the significant information content available in eyehand-head coordination and, as such, open up an exciting new direction for learning-based gaze estimation.