UENR-600K: A Large-Scale Physically Grounded Dataset for Nighttime Video Deraining

TL;DR

The paper introduces UENR-600K, a large-scale, physically realistic nighttime video deraining dataset created using Unreal Engine, enabling better generalization of deraining models to real-world scenarios.

Contribution

It presents a novel, large-scale, physically grounded dataset for nighttime video deraining, and establishes a new state-of-the-art baseline using a video-to-video generation approach.

Findings

Models trained on UENR-600K outperform previous datasets in real-world generalization.

The dataset captures realistic rain effects including color refractions and scene occlusions.

The proposed baseline nearly bridges the gap between synthetic and real nighttime rain videos.

Abstract

Nighttime video deraining is uniquely challenging because raindrops interact with artificial lighting. Unlike daytime white rain, nighttime rain takes on various colors and appears locally illuminated. Existing small-scale synthetic datasets rely on 2D rain overlays and fail to capture these physical properties, causing models to generalize poorly to real-world night rain. Meanwhile, capturing real paired nighttime videos remains impractical because rain effects cannot be isolated from other degradations like sensor noise. To bridge this gap, we introduce UENR-600K, a large-scale, physically grounded dataset containing 600,000 1080p frame pairs. We utilize Unreal Engine to simulate rain as 3D particles within virtual environments. This approach guarantees photorealism and physically real raindrops, capturing correct details like color refractions, scene occlusions, rain curtains. Leveraging this high-quality data, we establish a new state-of-the-art baseline by adapting the Wan 2.2 video generation model. Our baseline treat deraining as a video-to-video generation task, exploiting strong generative priors to almost entirely bridge the sim-to-real gap. Extensive benchmarking demonstrates that models trained on our dataset generalize significantly better to real-world videos. Project page: https://showlab.github.io/UENR-600K/.