Let's take this online: adapting scene coordinate regression network predictions for online RGB-D camera relocalisation
Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training trajectory, and the latter can struggle in textureless regio...
Main Authors: | Cavallari, T, Bertinetto, L, Mukhoti, J, Torr, P, Golodetz, S |
---|---|
Format: | Conference item |
Published: |
Institute of Electrical and Electronics Engineers
2019
|
Similar Items
-
On-the-fly adaptation of regression forests for online camera relocalisation
by: Cavallari, T, et al.
Published: (2017) -
Real-time RGB-D camera pose estimation in novel scenes using a relocalisation cascade
by: Cavallari, T, et al.
Published: (2019) -
Real-time RGB-D camera pose estimation in novel scenes using a relocalisation cascade
by: Cavallari, T, et al.
Published: (2018) -
Fast Scene Recognition and Camera Relocalisation for Wide Area Augmented Reality Systems
by: Tao Guan, et al.
Published: (2010-06-01) -
Probabilistic object reconstruction with online global model correction
by: Hunt, J, et al.
Published: (2018)