Implicit Euler ODE Networks for Single-Image Dehazing

TL;DR

This paper introduces an implicit Euler ODE-inspired neural network for single-image dehazing, leveraging a recursive IM-block and multi-level fusion to outperform existing methods.

Contribution

It extends the explicit Euler approach to an implicit scheme using a recursive neural network, achieving state-of-the-art dehazing performance.

Findings

Outperforms existing dehazing methods on benchmark datasets

Achieves state-of-the-art results in single-image dehazing

Demonstrates the effectiveness of implicit ODE-inspired networks

Abstract

Deep convolutional neural networks (CNN) have been applied for image dehazing tasks, where the residual network (ResNet) is often adopted as the basic component to avoid the vanishing gradient problem. Recently, many works indicate that the ResNet can be considered as the explicit Euler forward approximation of an ordinary differential equation (ODE). In this paper, we extend the explicit forward approximation to the implicit backward counterpart, which can be realized via a recursive neural network, named IM-block. Given that, we propose an efficient end-to-end multi-level implicit network (MI-Net) for the single image dehazing problem. Moreover, multi-level fusing (MLF) mechanism and residual channel attention block (RCA-block) are adopted to boost performance of our network. Experiments on several dehazing benchmark datasets demonstrate that our method outperforms existing methods and achieves the state-of-the-art performance.