Learning from Rendering: Realistic and Controllable Extreme Rainy Image Synthesis for Autonomous Driving Simulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Kaibin, Huang, Kaifeng, Deng, Hao, Tao, Zelin, Liu, Ziniu, Zhang, Lin, Zhao, Shengjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913967882895360
author Zhou, Kaibin
Huang, Kaifeng
Deng, Hao
Tao, Zelin
Liu, Ziniu
Zhang, Lin
Zhao, Shengjie
author_facet Zhou, Kaibin
Huang, Kaifeng
Deng, Hao
Tao, Zelin
Liu, Ziniu
Zhang, Lin
Zhao, Shengjie
contents Autonomous driving simulators provide an effective and low-cost alternative for evaluating or enhancing visual perception models. However, the reliability of evaluation depends on the diversity and realism of the generated scenes. Extreme weather conditions, particularly extreme rainfalls, are rare and costly to capture in real-world settings. While simulated environments can help address this limitation, existing rainy image synthesizers often suffer from poor controllability over illumination and limited realism, which significantly undermines the effectiveness of the model evaluation. To that end, we propose a learning-from-rendering rainy image synthesizer, which combines the benefits of the realism of rendering-based methods and the controllability of learning-based methods. To validate the effectiveness of our extreme rainy image synthesizer on semantic segmentation task, we require a continuous set of well-labeled extreme rainy images. By integrating the proposed synthesizer with the CARLA driving simulator, we develop CARLARain an extreme rainy street scene simulator which can obtain paired rainy-clean images and labels under complex illumination conditions. Qualitative and quantitative experiments validate that CARLARain can effectively improve the accuracy of semantic segmentation models in extreme rainy scenes, with the models' accuracy (mIoU) improved by 5% - 8% on the synthetic dataset and significantly enhanced in real extreme rainy scenarios under complex illuminations. Our source code and datasets are available at https://github.com/kb824999404/CARLARain/.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16421
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning from Rendering: Realistic and Controllable Extreme Rainy Image Synthesis for Autonomous Driving Simulation
Zhou, Kaibin
Huang, Kaifeng
Deng, Hao
Tao, Zelin
Liu, Ziniu
Zhang, Lin
Zhao, Shengjie
Computer Vision and Pattern Recognition
Autonomous driving simulators provide an effective and low-cost alternative for evaluating or enhancing visual perception models. However, the reliability of evaluation depends on the diversity and realism of the generated scenes. Extreme weather conditions, particularly extreme rainfalls, are rare and costly to capture in real-world settings. While simulated environments can help address this limitation, existing rainy image synthesizers often suffer from poor controllability over illumination and limited realism, which significantly undermines the effectiveness of the model evaluation. To that end, we propose a learning-from-rendering rainy image synthesizer, which combines the benefits of the realism of rendering-based methods and the controllability of learning-based methods. To validate the effectiveness of our extreme rainy image synthesizer on semantic segmentation task, we require a continuous set of well-labeled extreme rainy images. By integrating the proposed synthesizer with the CARLA driving simulator, we develop CARLARain an extreme rainy street scene simulator which can obtain paired rainy-clean images and labels under complex illumination conditions. Qualitative and quantitative experiments validate that CARLARain can effectively improve the accuracy of semantic segmentation models in extreme rainy scenes, with the models' accuracy (mIoU) improved by 5% - 8% on the synthetic dataset and significantly enhanced in real extreme rainy scenarios under complex illuminations. Our source code and datasets are available at https://github.com/kb824999404/CARLARain/.
title Learning from Rendering: Realistic and Controllable Extreme Rainy Image Synthesis for Autonomous Driving Simulation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.16421