Dynamic Scene Deblurring Based on Continuous Cross-Layer Attention Transmission

TL;DR

This paper introduces RDAFNet, a novel neural network architecture for dynamic scene deblurring that leverages a continuous cross-layer attention transmission mechanism to effectively utilize hierarchical attention information across layers.

Contribution

The paper proposes a new CCLAT mechanism and RDAFB module, enabling better attention information flow across layers, leading to improved deblurring performance.

Findings

Outperforms state-of-the-art deblurring methods on benchmark datasets.

Demonstrates the effectiveness of the CCLAT mechanism in capturing hierarchical attention.

Achieves superior visual quality in deblurred images.

Abstract

The deep convolutional neural networks (CNNs) using attention mechanism have achieved great success for dynamic scene deblurring. In most of these networks, only the features refined by the attention maps can be passed to the next layer and the attention maps of different layers are separated from each other, which does not make full use of the attention information from different layers in the CNN. To address this problem, we introduce a new continuous cross-layer attention transmission (CCLAT) mechanism that can exploit hierarchical attention information from all the convolutional layers. Based on the CCLAT mechanism, we use a very simple attention module to construct a novel residual dense attention fusion block (RDAFB). In RDAFB, the attention maps inferred from the outputs of the preceding RDAFB and each layer are directly connected to the subsequent ones, leading to a CCLAT mechanism. Taking RDAFB as the building block, we design an effective architecture for dynamic scene deblurring named RDAFNet. The experiments on benchmark datasets show that the proposed model outperforms the state-of-the-art deblurring approaches, and demonstrate the effectiveness of CCLAT mechanism.