← Search

Genki Kinoshita*

1 accepted papers

2024

Camera Height Doesn't Change: Unsupervised Training for Metric Monocular Road-Scene Depth Estimation

ECCV 2024poster

"In this paper, we introduce a novel training method for making any monocular depth network learn absolute scale and estimate metric road-scene depth just from regular training data, , driving videos. We refer to this training framework as FUMET. The key idea is to leverage cars found on the road as…

Cited by 2SourcePDFScholar