Lightweight Pyramid Networks for Image Deraining

Abstract

Existing deep convolutional neural networks have found major success in image deraining, but at the expense of an enormous number of parameters. This limits their potential application, for example in mobile devices. In this paper, we propose a lightweight pyramid of networks (LPNet) for single image deraining. Instead of designing a complex network structures, we use domain-specific knowledge to simplify the learning process. Specifically, we find that by introducing the mature Gaussian-Laplacian image pyramid decomposition technology to the neural network, the learning problem at each pyramid level is greatly simplified and can be handled by a relatively shallow network with few parameters. We adopt recursive and residual network structures to build the proposed LPNet, which has less than 8K parameters while still achieving state-of-the-art performance on rain removal. We also discuss the potential value of LPNet for other low- and high-level vision tasks.

arXiv commentsubmitted to IEEE Transactions on Neural Networks and Learning Systems

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Clearing the Skies: A deep network architecture for single-image rain removal
• MemNet: A Persistent Memory Network for Image Restoration
• DISC: Deep Image Saliency Computing via Progressive Representation Learning
• Convolutional Neural Pyramid for Image Processing

Cited by in corpus (4)

• Image De-raining Using a Conditional Generative Adversarial Network
• Progressive Image Deraining Networks: A Better and Simpler Baseline
• A Coarse-to-Fine Multi-stream Hybrid Deraining Network for Single Image Deraining
• Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution Network