Confidence Measure Guided Single Image De-raining

TL;DR

This paper introduces QuDeC, a novel single image de-raining method that uses a confidence measure to assess and process rain streaks based on local image quality, leading to improved removal performance.

Contribution

The paper proposes a confidence measure-guided network that learns rain content and image quality at different scales, addressing location information limitations of prior methods.

Findings

Significant improvement over state-of-the-art methods on synthetic datasets.

Effective handling of rain streaks with varying size, direction, and density.

Robust performance on real rainy images.

Abstract

Single image de-raining is an extremely challenging problem since the rainy images contain rain streaks which often vary in size, direction and density. This varying characteristic of rain streaks affect different parts of the image differently. Previous approaches have attempted to address this problem by leveraging some prior information to remove rain streaks from a single image. One of the major limitations of these approaches is that they do not consider the location information of rain drops in the image. The proposed Image Quality-based single image Deraining using Confidence measure (QuDeC), network addresses this issue by learning the quality or distortion level of each patch in the rainy image, and further processes this information to learn the rain content at different scales. In addition, we introduce a technique which guides the network to learn the network weights based on the confidence measure about the estimate of both quality at each location and residual rain streak information (residual map). Extensive experiments on synthetic and real datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art methods.