Directional Statistics and Filtering Using libDirectional

Kurz, Gerhard; Gilitschenski, Igor; Pfaff, Florian; Drude, Lukas; Hanebeck, Uwe D.; Haeb-Umbach, Reinhold; Siegwart, Roland Y.

doi:10.48550/arxiv.1712.09718

Cited by 1 publication

(1 citation statement)

References 50 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 4) to depend solely on Λ. To enable fast inference of F and gradient flow from Λ through F , we make use of a lookup table that is pre-computed based on a set of predefined range of values in Λ [58,60].…”

Section: Bingham Densitymentioning

confidence: 99%

Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation

Deng¹,

Bui²,

Navab³

et al. 2020

Preprint

View full text Add to dashboard Cite

In this work, we introduce Deep Bingham Networks (DBN), a generic framework that can naturally handle pose-related uncertainties and ambiguities arising in almost all real life applications concerning 3D data. While existing works strive to find a single solution to the pose estimation problem, we make peace with the ambiguities causing high uncertainty around which solutions to identify as the best. Instead, we report a family of poses which capture the nature of the solution space. DBN extends the state of the art direct pose regression networks by (i) a multi-hypotheses prediction head which can yield different distribution modes; and (ii) novel loss functions that benefit from Bingham distributions on rotations. This way, DBN can work both in unambiguous cases providing uncertainty information, and in ambiguous scenes where an uncertainty per mode is desired. On a technical front, our network regresses continuous Bingham mixture models and is applicable to both 2D data such as images and to 3D data such as point clouds. We proposed new training strategies so as to avoid mode or posterior collapse during training and to improve numerical

show abstract

Section: Bingham Densitymentioning

confidence: 99%