DrivingDepth achieves SOTA metric depth on nuScenes by residual pixel-wise scale correction on frozen foundation models using sparse LiDAR prompts, preserving geometric consistency.
Metri- cAnything: Scaling metric depth pretraining with noisy het- erogeneous sources.arXiv preprint arXiv:2601.22054, 2026
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
-
DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation
DrivingDepth achieves SOTA metric depth on nuScenes by residual pixel-wise scale correction on frozen foundation models using sparse LiDAR prompts, preserving geometric consistency.