Single Image Deraining: A Comprehensive Benchmark Analysis

Authors:
  • SLSiyuan Li
    Siyuan Li
  • IAIago Breno Araujo
    Iago Breno Araujo
  • WRWenqi Ren
    Wenqi Ren
  • ZWZhangyang Wang
    Zhangyang Wang
  • ETEric K. Tokuda
    Eric K. Tokuda
  • RJRoberto Hirata Junior
    Roberto Hirata Junior
  • RCRoberto Cesar-Junior
    Roberto Cesar-Junior
  • JZJiawan Zhang
    Jiawan Zhang
  • XGXiaojie Guo
    Xiaojie Guo
  • XCXiaochun Cao
    Xiaochun Cao
Preprint
Publisher website
Google Scholar
Abstract
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.
All Related Versions