High-resolution Rainy Image Synthesis: Learning from Rendering

Kaibin Zhou, Shengjie Zhao, Hao Deng, Lin Zhang

School of Software Engineering, Tongji University, Shanghai, China

Arxiv Preprint: https://arxiv.org/abs/2502.16421

Codes: Github

Datasets: Hugging Face , Google Drive , Baidu Cloud(Extraction Code: v9b2)

Introduction

This is the website for our paper "High-resolution Rainy Image Synthesis: Learning from Rendering".

HRI Dataset

Some rainy images of the HRI dataset.

• Lane Scene:



• Citystreet Scene:



• Japanesestreet Scene:

Source Codes and Data

• Get the codes: Github

• Get the HRI dataset and the Blender scene files: Hugging Face , Google Drive , Baidu Cloud(Extraction Code: v9b2)

Other Resources

Combining HRIGNet and CRIGNet, we developed CARLARain, an autonomous driving simulator framework that supports the simulation of rainy scenes in complex lighting environments.

• CRIGNet: Controllable Rain Streak Image Generation.
• CARLARain: A Rainy Autonomous Driving Simulator based on CARLA.

Last update: Feb. 26, 2025