ThermoHands: A Benchmark for 3D Hand Pose Estimation from Egocentric Thermal Image

arXiv:2403.09871v1 Announce Type: cross
Abstract: In this work, we present ThermoHands, a new benchmark for thermal image-based egocentric 3D hand pose estimation, aimed at overcoming challenges like varying lighting and obstructions (e.g., handwear). The benchmark includes a diverse dataset from 28 subjects performing hand-object and hand-virtual interactions, accurately annotated with 3D hand poses through an automated process. We introduce a bespoken baseline method, TheFormer, utilizing dual transformer modules for effective egocentric 3D hand pose estimation in thermal imagery. Our experimental …

abstract arxiv benchmark challenges cs.ai cs.cv cs.hc cs.lg dataset diverse image interactions lighting object type virtual work