How Hard Is Snow? A Paired Domain Adaptation Dataset for Clear and Snowy Weather: CADC+

TL;DR

This paper introduces CADC+, a paired dataset capturing the same driving scenes in clear and snowy conditions to evaluate the impact of snow on 3D object detection, addressing limitations of synthetic data and domain shift.

Contribution

CADC+ is the first paired weather domain adaptation dataset for winter driving, enabling more accurate evaluation of snow effects on perception systems.

Findings

Snow increases uncertainty in 3D detection, acting as noise and a separate domain.

Paired data reduces confounding factors, improving evaluation accuracy.

Preliminary results highlight the impact of snow on detection performance.

Abstract

The impact of snowfall on 3D object detection performance remains underexplored. Conducting such an evaluation requires a dataset with sufficient labelled data from both weather conditions, ideally captured in the same driving environment. Current driving datasets with LiDAR point clouds either do not provide enough labelled data in both snowy and clear weather conditions, or rely on de-snowing methods to generate synthetic clear weather. Synthetic data often lacks realism and introduces an additional domain shift that confounds accurate evaluations. To address these challenges, we present CADC+, the first paired weather domain adaptation dataset for autonomous driving in winter conditions. CADC+ extends the Canadian Adverse Driving Conditions dataset (CADC) using clear weather data that was recorded on the same roads and in the same period as CADC. To create CADC+, we pair each CADC sequence with a clear weather sequence that matches the snowy sequence as closely as possible. CADC+ thus minimizes the domain shift resulting from factors unrelated to the presence of snow. We also present some preliminary results using CADC+ to evaluate the effect of snow on 3D object detection performance. We observe that snow introduces a combination of aleatoric and epistemic uncertainties, acting as both noise and a distinct data domain.