FlexDepth proposes a scale-driven family of self-supervised MDE models with two-stage training and SDD decoder claiming SOTA performance and low compute on driving benchmarks.
Our reproduction of DA2 using the official inference pipeline yields slightly better results than the values reported in [47] (e.g., Abs Rel 0.070 vs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation
FlexDepth proposes a scale-driven family of self-supervised MDE models with two-stage training and SDD decoder claiming SOTA performance and low compute on driving benchmarks.