Dual-Focus Residual Tensor Enhancement Network for Infrared Small Target Detection

Infrared small target detection (IRSTD) remains a challenging task due to the inherent limitations of complex backgrounds and the absence of distinct target features. To address these challenges, we propose a dual-focus residual tensor enhancement network (DRTENet) which integrates edge enhancement and noise suppression. We propose a residual tensor-weighting module (RTWM) that computes the local structure tensors to yield edge-saliency maps and integrates a residual learning strategy to preserve target contours and suppress background clutters. Based on RTWM, we construct a Gaussian pyramid encoder to excavate multiscale edge features and smooth point noise. Furthermore, we propose a dual-focus optimization module (DFOM) that designs a two-branch structure to enhance small targets powered by local semantic content, while simultaneously reducing background noise through the global contextual information. Extensive experiments on several public infrared datasets demonstrate the effectiveness of DRTENet, achieving state-of-the-art detection performance. The source code is publicly available at: https://github.com/MJW66/DRTENet