User: Guest  Login
Document type:
Konferenzbeitrag 
Contribution type:
Elektronisches Dokument 
Author(s):
Ruhkamp, Patrick; Gao, Daoyi; Chen, Hanzhi; Navab, Nassir; Busam, Benjamin 
Title:
Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation 
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...    »
 
Keywords:
3DV, Monocular Depth Estimation, Depth Consistency, Spatial-Temporal Attention 
Book / Congress title:
International Conference on 3D Vision 
Year:
2021