Single Image Deraining: A Comprehensive Benchmark Analysis

By Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K. Tokuda, Roberto Hirata Junior, Roberto Marcondes Cesar Junior, Jiawan Zhang, Xiaojie Guo, Xiaochun Cao. Computer Vision and Pattern Recognition, 2019

358 citations recorded by the source corpus.

We present a comprehensive study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark consisting of both synthetic and real-world rainy images.This dataset highlights diverse data sources and image contents, and is divided into three subsets (rain streak, rain drop, rain and mist), each serving different training or evaluation purposes. We further provide a rich variety of criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference metrics, to subjective evaluation and the novel task-driven evaluation. Experiments on the dataset shed light on the comparisons and limitations of state-of-the-art deraining algorithms, and suggest promising future directions.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fbc0b44b7a93721978a362465a3046646b075e57

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Advancing Image Understanding in Poor Visibility Environments: A Collective Benchmark Study (2019, background): “That concurs with the conclusion drawn from the recent benchmark work [74]: “Perhaps surprisingly at the first glance, we find”
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better (2019, methodology): “We ﬁt a Bradley-Terry model [3] to estimate the subjective score for each method so that they can be ranked, with the identical routine following the previous benchmark work [24, 26].”
A Model-Driven Deep Neural Network for Single Image Rain Removal (2020, background): “Hence, removing rain streaks from rainy images is an important pre-processing task and has drawn much research attention in the recent years [39, 26].”
MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video (2019, background): “Recently, with its success in computer vision [2, 15, 23] and natural language processing [9, 32], neural networks are increasingly used in the multi-modal domain, especially on multimodal representations [10, 11, 35–37, 43].”
EnlightenGAN: Deep Light Enhancement Without Paired Supervision (2019, background): “Image enhancement as pre-processing for improving subsequent high-level vision tasks has recently received increasing attention [28, 49, 50], with a number of benchmarking efforts [47, 51, 52].”
Image Restoration with Mean-Reverting Stochastic Differential Equations (2023, methodology): “Common specific examples include image deraining (Li et al., 2019; Ren et al., 2019), deblurring (Nah et al., 2017; Zhang et al., 2020), denoising (Zhang et al., 2017a; 2018a), and super-resolution (Dong et al., 2015; Lugmayr et al., 2020; Luo et al., 2022a), just to mention a few.”
GAN-Knowledge Distillation for One-Stage Object Detection (2019, background): “[38] conducted a study of object detection in rainy days.”
Image De-raining via Continual Learning (2021, background): “object detection, image classification, person identification, and more [20, 12, 4, 24, 19, 31, 34].”
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors (2021, methodology): “Image dehazing could be used as a preprocessing step for these high-level tasks, and the resulting task performance could in turn become a downstream task performance indicator, as [13, 16, 19] suggested.”
Uformer: A General U-Shaped Transformer for Image Restoration (2021, background): “More CNN-based image restoration architectures can be found in the recent surveys [32, 57, 65] and the NTIRE Challenges [2].”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, background): “Data-driven dehazing models recently become popular due to the success of machine learning in various vision applications (Ren et al. 2018; Li et al. 2019).”
Restormer: Efficient Transformer for High-Resolution Image Restoration (2021, methodology): “We refer the reader to NTIRE challenge reports [2,5,30,57] and recent literature reviews [8,42,73], which summarize major design choices for image restoration.”