Learning a Depth Covariance Function

Andrew J. Davison; Eric Dexheimer

REVIEW

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.12157 v2 pith:MQCRXTMQ submitted 2023-03-21 cs.CV cs.LGcs.RO

Learning a Depth Covariance Function

Eric Dexheimer , Andrew J. Davison This is my paper

classification cs.CV cs.LGcs.RO

keywords depthcovariancefunctiongivenlearningselectiontasksactive

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

We propose learning a depth covariance function with applications to geometric vision tasks. Given RGB images as input, the covariance function can be flexibly used to define priors over depth functions, predictive distributions given observations, and methods for active point selection. We leverage these techniques for a selection of downstream tasks: depth completion, bundle adjustment, and monocular dense visual odometry.

Learning a Depth Covariance Function

discussion (0)