Introduces the ASTAD task and training-free ASTModel framework for semantically consistent asymmetric style transfer using labeled synthetic content and unlabeled real references.
A style-based metric for quantifying the synthetic-to-real gap in autonomous driving image datasets,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces a path-based credibility framework using equivalent rainfall intensity, RRD scores from real raindrop spectra, and lidar consistency metrics to identify preferable simulated rainfall paths for AV perception tests.
citing papers explorer
-
ASTAD: Asymmetric Style Transfer for Synthetic-to-Real Adaptation in Autonomous Driving
Introduces the ASTAD task and training-free ASTModel framework for semantically consistent asymmetric style transfer using labeled synthetic content and unlabeled real references.
-
From Nominal Intensity to Equivalent Rainfall: A Path-Based Credibility Evaluation Framework for Simulated Rainfall in Autonomous-Driving Perception Tests
Introduces a path-based credibility framework using equivalent rainfall intensity, RRD scores from real raindrop spectra, and lidar consistency metrics to identify preferable simulated rainfall paths for AV perception tests.