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…