Denoising Distillation Makes Event-Frame Transformers as Accurate Gaze Trackers

arXiv:2404.00548v1 Announce Type: new
Abstract: This paper tackles the problem of passive gaze estimation using both event and frame data. Considering inherently different physiological structures, it's intractable to accurately estimate purely based on a given state. Thus, we reformulate the gaze estimation as the quantification of state transitions from the current state to several prior registered anchor states. Technically, we propose a two-stage learning-based gaze estimation framework to divide the whole gaze estimation process into a coarse-to-fine process of anchor …

arxiv cs.cv denoising distillation event transformers type