Exploiting uncertainty in regression forests for accurate camera relocalization
Recent advances in camera relocalization use predictions from a regression forest to guide the camera pose optimization procedure. In these methods, each tree associates one pixel with a point in the scene's 3D world coordinate frame. In previous work, these predictions were point estimates and...
Κύριοι συγγραφείς: | Valentin, J, Nießner, M, Shotton, J, Fitzgibbon, A, Izadi, S, Torr, P |
---|---|
Μορφή: | Conference item |
Γλώσσα: | English |
Έκδοση: |
IEEE
2015
|
Παρόμοια τεκμήρια
Παρόμοια τεκμήρια
-
On-the-fly adaptation of regression forests for online camera relocalisation
ανά: Cavallari, T, κ.ά.
Έκδοση: (2017) -
SemanticPaint: interactive segmentation and learning of 3D world
ανά: Valentin, J, κ.ά.
Έκδοση: (2015) -
SemanticPaint: interactive 3D labeling and learning at your fingertips
ανά: Valentin, J, κ.ά.
Έκδοση: (2015) -
Mondrian Forests for Large-Scale Regression when Uncertainty Matters
ανά: Lakshminarayanan, B, κ.ά.
Έκδοση: (2016) -
Automatic camera tracking
ανά: Fitzgibbon, AW, κ.ά.
Έκδοση: (2013)