Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network
Sifei Liu, Jinshan Pan, Ming-Hsuan Yang

Abstract: In this paper, we consider numerous low-level vision problems (e.g., edge-preserving filtering and denoising) as recursive image filtering via a hybrid neural network.​ The network contains several spatially variant recurrent neural networks (RNN) as equivalents of a group of distinct recursive filters for each pixel, and a deep convolutional neural network (CNN) that learns the weights of RNNs.​ The deep CNN can learn regulations of recurrent propagation for various tasks and effectively guides recurrent propagation over an entire image.​ The proposed model does not need a large number of convolutional channels nor big kernels to learn features for low-level vision filters. It is significantly smaller and faster in comparison with a deep CNN based image filter.​ Experimental results show that many low-level vision tasks can be effectively learned and carried out in real-time by the proposed algorithm.

Related links: [Paper][Supp][Poster][Slides]

Codes and pretrained models can be found from my github.

Model Architecture

Video Demo