Research papers · 2026
Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
Overview
FlexDepth separates static and dynamic training and adapts decoder components to model scale. Driving-benchmark and mobile evaluations examine efficient monocular depth estimation, confidence handling and generalization in challenging road environments.
Author-supplied source information
Author-supplied information on arXiv.
Computer Vision - ECCV 2026, Lecture Notes in Computer Science, vol. 17003, Springer, Cham, 2026
Accepted by ECCV2026. Code is available at https://github.com/startnew/flexdepth
Version: arXiv v3 — manuscript revision