Skip to content
← All publications
CVPR 2021

Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End

Abdelrahman Eldesokey, Michael Felsberg, Karl Holmquist, Michael Persson

Abstract

Introduces a depth-completion approach that propagates uncertainty estimates end-to-end through the network, improving reliability of depth predictions from sparse LiDAR input.

Computer VisionUncertainty EstimationDepth Estimation