GradDT: Gradient-Guided Despeckling Transformer for Industrial Imaging Sensors

Despeckling is a longstanding topic in industrial imaging sensors. The speckle noise is a granular disturbance that often brings negative side effects on the detection and recognition of targets of interest. From the statistical point of view, this type of noise can be modeled as a multiplicative formula. The nonlinear multiplicative property makes despeckling more intractable with respect to noise reduction and details preservation. To blindly remove the undesirable speckle noise, we combine the gradient model and machine learning technology for despeckling. In particular, we first introduce the logarithmic transformation to transform the multiplicative speckle noise into an additive version. A gradient-guided despeckling transformer (termed GradDT) is then proposed to blindly reduce the additive noise in the transformed noisy images. To be specific, the proposed method mainly includes two modules, i.e., the spatial feature extraction module (SFEM) and the efficient transformer module (ETM). The SFEM can extract the spatial feature of speckle noise and the gradient maps corresponding to the noise-free image. The ETM module can calculate the spatial domain's cross-channel cross-covariance and produce global attention maps to reconstruct the sharp image. The proposed GradDT thus can effectively distinguish the speckle noise and vital image features (e.g., edge and texture) to balance the degree of noise suppression and details preservation. Extensive experiments have been implemented on both synthetic and realistic degraded images. Compared with several state-of-the-art speckle noise reduction methods, our GradDT could generate superior imaging performance in terms of both quantitative evaluation and visual quality. The source code is available at https://github.com/LouisYuxuLu/GradDT.