Single Image Deraining: From Model-Based to Data-Driven and Beyond

TL;DR

This paper provides a comprehensive survey of single-image deraining techniques, tracing the evolution from model-based to data-driven methods, and discusses their architectures, datasets, and future research directions.

Contribution

It offers a detailed review of deraining methods over the past decade, highlighting the transition from traditional priors to deep learning approaches and analyzing their performance.

Findings

Deep learning methods outperform traditional priors in deraining quality.

Data-driven approaches utilize advanced architectures and large datasets.

Performance comparisons show significant improvements over earlier methods.

Abstract

The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining methods employ a cost function, where various priors are developed to represent the properties of rain and background layers. Since 2017, single-image deraining methods step into a deep-learning era, and exploit various types of networks, i.e. convolutional neural networks, recurrent neural networks, generative adversarial networks, etc., demonstrating impressive performance. Given the current rapid development, in this paper, we provide a comprehensive survey of deraining methods over the last decade. We summarize the rain appearance models, and discuss two categories of deraining approaches: model-based and data-driven approaches. For the former, we organize the literature based on their basic models and priors. For the latter, we discuss developed ideas related to architectures, constraints, loss functions, and training datasets. We present milestones of single-image deraining methods, review a broad selection of previous works in different categories, and provide insights on the historical development route from the model-based to data-driven methods. We also summarize performance comparisons quantitatively and qualitatively. Beyond discussing the technicality of deraining methods, we also discuss the future directions.