Learning with 3D rotations, a hitchhiker's guide to SO(3)

arXiv:2404.11735v1 Announce Type: new
Abstract: Many settings in machine learning require the selection of a rotation representation. However, choosing a suitable representation from the many available options is challenging. This paper acts as a survey and guide through rotation representations. We walk through their properties that harm or benefit deep learning with gradient-based optimization. By consolidating insights from rotation-based learning, we provide a comprehensive overview of learning functions with rotation representations. We provide guidance on selecting representations based on whether …

abstract arxiv benefit cs.cv cs.lg cs.ro deep learning guide harm however machine machine learning paper representation rotation survey through type