Open access
Datum
2020-09-10Typ
- Conference Paper
ETH Bibliographie
yes
Altmetrics
Abstract
Traditionally, appearance-based gaze estimation methods use statically defined face
regions as input to the gaze estimator, such as eye patches, and therefore suffer from
difficult lighting conditions and extreme head poses for which these regions are often
not the most informative with respect to the gaze estimation task. We posit that facial
regions should be selected dynamically based on the image content and propose a novel
gaze estimation method that combines the task of region proposal and gaze estimation
into a single end-to-end trainable framework. We introduce a novel loss that allows for
unsupervised training of a region proposal network alongside the (supervised) training of
the final gaze estimator. We show that our method can learn meaningful region selection
strategies and outperforms fixed region approaches. We further show that our method
performs particularly well for challenging cases, i.e., those with difficult lighting conditions such as directional lights, extreme head angles, or self-occlusion. Finally, we show
that the proposed method achieves better results than the current state-of-the-art method
in within and cross-dataset evaluations. Mehr anzeigen
Persistenter Link
https://doi.org/10.3929/ethz-b-000455196Publikationsstatus
publishedBuchtitel
31st British Machine Vision Conference (BMVC 2020)Seiten / Artikelnummer
Verlag
British Machine Vision AssociationKonferenz
Organisationseinheit
03979 - Hilliges, Otmar / Hilliges, Otmar
Zugehörige Publikationen und Daten
Anmerkungen
Poster presentation on September 10, 2020. Due to the Coronavirus (COVID-19) the conference was conducted virtually.ETH Bibliographie
yes
Altmetrics