SynthRSF (Part 1) - A Novel Photorealistic Synthetic Dataset for Adverse Weather Condition Denoising

SynthRSF Dataset - Part 1 of 2

Contents

SynthRSF (Parts 1, 2):

26,893 photorealistic image pairs (noisy and ground truth).

14 3D scenes set in various environmental (rural/urban), contextual (indoor/outdoor) and lighting conditions (day/night).

Created using Unreal 5.2 engine.

SynthRSF-MM expansion:

13,800 additional pairs are accompanied by:

16-bit depth maps.

Pixel-accurate object annotations for 41 object classes.

Overview

SynthRSF (Synthetic with Rain, Snow, uniform and non-uniform Fog) dataset is introduced for training and evaluating adverse weather image denoising models as well as use in object detection, semantic segmentation, and depth estimation models.

SynthRSF addresses a gap in synthetic datasets for adverse weather conditions, contributing significantly more photorealistic data compared to common 2D layered noise datasets, as well as additional modalities.

Applications include autonomous driving, surveillance, robotics, computer-assisted search-and-rescue.