Nonuniformity and Bad Pixel Correction Based on 3-D Network With Oversmoothing Suppression

The purpose of non-uniformity and blind pixel correction is to provide a more reliable foundation for subsequent image processing and target detection. Existing correction methods generally struggle to balance the contradiction between over-smoothing and residual noise. Particularly, over-smoothing can easily filter out texture details and dim small targets. Based on the multi-frame response model of infrared focal plane array detector, we propose a two-stage 3-D residual fully convolutional network for correction factor estimation, integrated with an over-smoothing suppression mechanism. The proposed method designs two 3-D sub-networks to estimate the gain correction factors and offset correction factors respectively. For the correction factor pre-estimation tensors outputted by the two sub-networks, an inter-frame averaging after outlier removal is applied to suppress over-smoothing. Ultimately, using multiplication and addition structures, the final estimated values of the gain and offset correction factors can be utilized to obtain the corrected images. Experimental results indicate that the proposed method exhibits substantial generalization capabilities towards different intensities non-uniformity pixel-wise fixed mode noise and can effectively correct the blind pixels of real infrared images while suppressing over-smoothing and maintaining the image details such as dim small targets well. Overall, as a method that combines the model-driven and the data-driven, our method possesses strong theoretical interpretability and superior performance.