Confidence Measure Guided Single Image De-raining

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.

arXiv commentTIP2019 submission. arXiv admin note: substantial text overlap with arXiv:1906.11129

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Robust Recovery of Subspace Structures by Low-Rank Representation
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Clearing the Skies: A deep network architecture for single-image rain removal
• Image De-raining Using a Conditional Generative Adversarial Network
• FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors
• Multi-style Generative Network for Real-time Transfer
• Deblurring Face Images using Uncertainty Guided Multi-Stream Semantic Networks

Cited by in corpus (8)

• A Survey on Rain Removal from Video and Single Image
• Exploring Overcomplete Representations for Single Image Deraining using CNNs
• Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network
• Memory-guided Image De-raining Using Time-Lapse Data
• Semi-Supervised Image Deraining using Gaussian Processes
• Structural Residual Learning for Single Image Rain Removal
• Confidence-guided Lesion Mask-based Simultaneous Synthesis of Anatomic and Molecular MR Images in Patients with Post-treatment Malignant Gliomas
• Controllable Confidence-Based Image Denoising