CredibleDFGO extends DFGO by training a weighting network with NLL and energy score supervision so that the Hessian-derived covariances better match actual positioning errors on UrbanNav scenes.
Victor Dheur and Souhaib Ben Taieb
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Systematic benchmarking reveals that regression calibration metrics frequently disagree on recalibration quality, with ENCE and CWC identified as more consistent performers.
citing papers explorer
-
CredibleDFGO: Differentiable Factor Graph Optimization with Credibility Supervision
CredibleDFGO extends DFGO by training a weighting network with NLL and energy score supervision so that the Hessian-derived covariances better match actual positioning errors on UrbanNav scenes.