EAR-Net: Pursuing End-to-End Absolute Rotations from Multi-View Images

arXiv:2310.10051v2 Announce Type: replace
Abstract: Absolute rotation estimation is an important topic in 3D computer vision. Existing works in literature generally employ a multi-stage (at least two-stage) estimation strategy where multiple independent operations (feature matching, two-view rotation estimation, and rotation averaging) are implemented sequentially. However, such a multi-stage strategy inevitably leads to the accumulation of the errors caused by each involved operation, and degrades its final estimation on global rotations accordingly. To address this problem, we propose an End-to-end method …

abstract arxiv computer computer vision cs.cv feature however images independent leads least literature multiple operations rotation stage strategy type view vision