Back to List

Weakly-Supervised Physically Unconstrained Gaze Estimation

Rakshit Kothari et al. — CVPR (2021)

Abstract


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.

Read the full paper
AUTHORS

Rakshit Kothari1,2* Shalini De Mello1 Umar Iqbal1 Wonmin Byeon1 Seonwook Park3 Jan Kautz1

1NVIDIA, 2Rochester Institute of Technology, 3Lunit Inc.

PUBLISHED
CVPR (2021)

Read more