Fixed Pattern Noise Reduction for Infrared Images Based on Cascade Residual Attention CNN

TL;DR

This paper introduces a cascade residual attention CNN model for infrared fixed pattern noise reduction that operates on single frames without parameter tuning, improving visual quality and quantitative metrics.

Contribution

The paper proposes a novel cascade CNN with residual skip connections and a spatial-channel noise attention unit for more effective fixed pattern noise reduction in infrared images.

Findings

Outperforms existing methods in visual quality

Achieves better quantitative assessment results

Operates effectively without parameter tuning

Abstract

Existing fixed pattern noise reduction (FPNR) methods are easily affected by the motion state of the scene and working condition of the image sensor, which leads to over smooth effects, ghosting artifacts as well as slow convergence rate. To address these issues, we design an innovative cascade convolution neural network (CNN) model with residual skip connections to realize single frame blind FPNR operation without any parameter tuning. Moreover, a coarse-fine convolution (CF-Conv) unit is introduced to extract complementary features in various scales and fuse them to pick more spatial information. Inspired by the success of the visual attention mechanism, we further propose a particular spatial-channel noise attention unit (SCNAU) to separate the scene details from fixed pattern noise more thoroughly and recover the real scene more accurately. Experimental results on test data demonstrate that the proposed cascade CNN-FPNR method outperforms the existing FPNR methods in both of visual effect and quantitative assessment.