Fixed Pattern Noise Reduction for Infrared Images Based on Cascade Residual Attention CNN
This work addresses noise reduction in infrared imaging, which is important for applications like surveillance and medical imaging, but it appears incremental as it builds on existing CNN and attention mechanisms.
The paper tackled fixed pattern noise reduction in infrared images by proposing a cascade CNN with residual connections, coarse-fine convolution, and a spatial-channel noise attention unit, resulting in improved visual effects and quantitative assessment compared to existing methods.
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.