Conditional Variational Image Deraining

Abstract

Image deraining is an important yet challenging image processing task. Though deterministic image deraining methods are developed with encouraging performance, they are infeasible to learn flexible representations for probabilistic inference and diverse predictions. Besides, rain intensity varies both in spatial locations and across color channels, making this task more difficult. In this paper, we propose a Conditional Variational Image Deraining (CVID) network for better deraining performance, leveraging the exclusive generative ability of Conditional Variational Auto-Encoder (CVAE) on providing diverse predictions for the rainy image. To perform spatially adaptive deraining, we propose a spatial density estimation (SDE) module to estimate a rain density map for each image. Since rain density varies across different color channels, we also propose a channel-wise (CW) deraining scheme. Experiments on synthesized and real-world datasets show that the proposed CVID network achieves much better performance than previous deterministic methods on image deraining. Extensive ablation studies validate the effectiveness of the proposed SDE module and CW scheme in our CVID network. The code is available at \url{https://github.com/Yingjun-Du/VID}.

14pages, 11 figures, 5 tables, newly accepted by TIP

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Auto-Encoding Variational Bayes
• Conditional Generative Adversarial Nets
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Empirical Evaluation of Rectified Activations in Convolutional Network
• Clearing the Skies: A deep network architecture for single-image rain removal
• STAR: A Structure and Texture Aware Retinex Model
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• Semi-supervised Transfer Learning for Image Rain Removal
• Learning to Learn Kernels with Variational Random Features

Cited by in corpus (8)

• Noisy-As-Clean: Learning Self-supervised Denoising from the Corrupted Image
• Exploring Overcomplete Representations for Single Image Deraining using CNNs
• Multi-scale Attentive Image De-raining Networks via Neural Architecture Search
• Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network
• EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
• SDNet: mutil-branch for single image deraining using swin
• Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation
• A General Divergence Modeling Strategy for Salient Object Detection