Accurate and lightweight dehazing via multi-receptive-field non-local network and novel contrastive regularization

TL;DR

This paper introduces a lightweight deep learning model for image dehazing that combines multi-scale feature extraction, attention mechanisms, long-range dependency capture, and contrastive regularization, achieving superior performance with fewer parameters.

Contribution

The paper proposes a novel multi-receptive-field non-local network with a new contrastive regularization for improved dehazing performance and efficiency.

Findings

Outperforms recent state-of-the-art methods in dehazing.

Uses less than 1.5 million parameters.

Effectively captures multi-scale features and long-range dependencies.

Abstract

Recently, deep learning-based methods have dominated image dehazing domain. A multi-receptive-field non-local network (MRFNLN) consisting of the multi-stream feature attention block (MSFAB) and the cross non-local block (CNLB) is presented in this paper to further enhance the performance. We start with extracting richer features for dehazing. Specifically, a multi-stream feature extraction (MSFE) sub-block, which contains three parallel convolutions with different receptive fields (i.e., $1\times 1$, $3\times 3$, $5\times 5$), is designed for extracting multi-scale features. Following MSFE, an attention sub-block is employed to make the model adaptively focus on important channels/regions. These two sub-blocks constitute our MSFAB. Then, we design a cross non-local block (CNLB), which can capture long-range dependencies beyond the query. Instead of the same input source of query branch, the key and value branches are enhanced by fusing more preceding features. CNLB is computation-friendly by leveraging a spatial pyramid down-sampling (SPDS) strategy to reduce the computation and memory consumption without sacrificing the performance. Last but not least, a novel detail-focused contrastive regularization (DFCR) is presented by emphasizing the low-level details and ignoring the high-level semantic information in a representation space specially designed for dehazing. Comprehensive experimental results demonstrate that the proposed MRFNLN model outperforms recent state-of-the-art dehazing methods with less than 1.5 Million parameters.