MMD-LoRA uses text-guided LoRA adapters and contrastive learning to adapt a depth estimator to unseen adverse weather conditions, setting new reported numbers on nuScenes and Oxford RobotCar.
Diffusion models for monoc- ular depth estimation: Overcoming challenging conditions,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Multi-Modality Driven LoRA for Adverse Condition Depth Estimation
MMD-LoRA uses text-guided LoRA adapters and contrastive learning to adapt a depth estimator to unseen adverse weather conditions, setting new reported numbers on nuScenes and Oxford RobotCar.