Weakly-Supervised Physically Unconstrained Gaze Estimation
This addresses the challenge of acquiring training data for physically unconstrained gaze estimation in in-the-wild scenarios, offering a novel weakly-supervised approach that is incremental but impactful for computer vision applications.
The paper tackles the problem of weakly-supervised gaze estimation from videos of human interactions, leveraging 'looking at each other' activity labels to provide 3D gaze supervision, resulting in significant improvements in accuracy and cross-domain generalization on the Gaze360 benchmark.
A major challenge for physically unconstrained gaze estimation is acquiring training data with 3D gaze annotations for in-the-wild and outdoor scenarios. In contrast, videos of human interactions in unconstrained environments are abundantly available and can be much more easily annotated with frame-level activity labels. In this work, we tackle the previously unexplored problem of weakly-supervised gaze estimation from videos of human interactions. We leverage the insight that strong gaze-related geometric constraints exist when people perform the activity of "looking at each other" (LAEO). To acquire viable 3D gaze supervision from LAEO labels, we propose a training algorithm along with several novel loss functions especially designed for the task. With weak supervision from two large scale CMU-Panoptic and AVA-LAEO activity datasets, we show significant improvements in (a) the accuracy of semi-supervised gaze estimation and (b) cross-domain generalization on the state-of-the-art physically unconstrained in-the-wild Gaze360 gaze estimation benchmark. We open source our code at https://github.com/NVlabs/weakly-supervised-gaze.