Bridging Clear and Adverse Driving Conditions
By: Yoel Shapiro, Yahia Showgan, Koustav Mullick
Potential Business Impact:
Makes self-driving cars see better in bad weather.
Autonomous Driving (AD) systems exhibit markedly degraded performance under adverse environmental conditions, such as low illumination and precipitation. The underrepresentation of adverse conditions in AD datasets makes it challenging to address this deficiency. To circumvent the prohibitive cost of acquiring and annotating adverse weather data, we propose a novel Domain Adaptation (DA) pipeline that transforms clear-weather images into fog, rain, snow, and nighttime images. Here, we systematically develop and evaluate several novel data-generation pipelines, including simulation-only, GAN-based, and hybrid diffusion-GAN approaches, to synthesize photorealistic adverse images from labelled clear images. We leverage an existing DA GAN, extend it to support auxiliary inputs, and develop a novel training recipe that leverages both simulated and real images. The simulated images facilitate exact supervision by providing perfectly matched image pairs, while the real images help bridge the simulation-to-real (sim2real) gap. We further introduce a method to mitigate hallucinations and artifacts in Stable-Diffusion Image-to-Image (img2img) outputs by blending them adaptively with their progenitor images. We finetune downstream models on our synthetic data and evaluate them on the Adverse Conditions Dataset with Correspondences (ACDC). We achieve 1.85 percent overall improvement in semantic segmentation, and 4.62 percent on nighttime, demonstrating the efficacy of our hybrid method for robust AD perception under challenging conditions.
Similar Papers
Bridging Clear and Adverse Driving Conditions
CV and Pattern Recognition
Makes self-driving cars see in bad weather.
Adverse Weather-Independent Framework Towards Autonomous Driving Perception through Temporal Correlation and Unfolded Regularization
Robotics
Enables self-driving cars to see in fog and rain
Adversarial Appearance Learning in Augmented Cityscapes for Pedestrian Recognition in Autonomous Driving
CV and Pattern Recognition
Makes self-driving cars better at seeing people.