Benutzer: Gast  Login
Titel:

Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation

Dokumenttyp:
Konferenzbeitrag
Art des Konferenzbeitrags:
Elektronisches Dokument
Autor(en):
Ruhkamp, Patrick; Gao, Daoyi; Chen, Hanzhi; Navab, Nassir; Busam, Benjamin
Abstract:
Inferring geometrically consistent dense 3D scenes across a tuple of temporally consecutive images remains challenging for self-supervised monocular depth prediction pipelines. This paper explores how the increasingly popular transformer architecture, together with novel regularized loss formulations, can improve depth consistency while preserving accuracy. We propose a spatial attention module that correlates coarse depth predictions to aggregate local geometric information. A novel temporal at...     »
Stichworte:
3DV, Monocular Depth Estimation, Depth Consistency, Spatial-Temporal Attention
Kongress- / Buchtitel:
International Conference on 3D Vision
Jahr:
2021
 BibTeX