Lightweight Pyramid Networks for Image Deraining

By Xueyang Fu, Borong Liang, Yue Huang, Xinghao Ding, John William Paisley. IEEE Transactions on Neural Networks and Learning Systems, 2018

396 citations recorded by the source corpus.

Existing deep convolutional neural networks (CNNs) have found major success in image deraining, but at the expense of an enormous number of parameters. This limits their potential applications, e.g., in mobile devices. In this paper, we propose a lightweight pyramid networt (LPNet) for single-image deraining. Instead of designing a complex network structure, we use domain-specific knowledge to simplify the learning process. In particular, 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 the state-of-the-art performance on rain removal. We also discuss the potential value of LPNet for other low- and high-level vision tasks.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/ae2e98325f301182a80f634fa3d0830546adead2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Pre-Trained Image Processing Transformer (2020, background): “A various excellent works are also proposed for the other tasks, such as denoising [68, 32, 37, 45, 24], dehazing [6, 46, 85, 80], deraining [36, 78, 62, 29, 74, 47], and debluring [67, 53, 23, 10].”
Progressive Image Deraining Networks: A Better and Simpler Baseline (2019, background): “Moreover, several models are designed to improve computational efficiency by utilizing lightweight networks in a cascaded scheme [4] or a Laplacian pyramid framework [7], but at the cost of obvious degradation in deraining performance.”
Image De-raining via Continual Learning (2021, background): “object detection, image classification, person identification, and more [20, 12, 4, 24, 19, 31, 34].”
Semi-Supervised Transfer Learning for Image Rain Removal (2018, methodology): “Recently, deep learning methods [9, 10, 29, 32, 31, 23, 12, 11, 8] have been empirically sub-stantiated to achieve state-of-the-art performance for SIRR by training an appropriate, carefully designed network to detect and remove the rain streaks simultaneously.”
Multi-Stage Progressive Image Restoration (2021, methodology): “These methods [24, 47, 53, 63, 70, 71, 88, 99] aim to recover clean image in a progressive manner by employing a light-weight subnetwork at each stage.”
All-In-One Image Restoration for Unknown Corruption (2022, methodology): “To this end, we choose five IRSD methods (i.e., BRDNet [40], LPNet [11], FDGAN [7] and MPRNet [51]) and one IRMD method (i.e., DL [8]) as baselines.”
HINet: Half Instance Normalization Network for Image Restoration (2021, background): “[11] introduce the mature Gaussian-Laplacian image pyramid decomposition technology to the neural network, and uses a relatively shallow network to handle the learning problem at each pyramid level.”
Multi-Scale Progressive Fusion Network for Single Image Deraining (2020, methodology): “Unlike [8] completing the deraining task from each individual resolution level, Zheng et al .”