Infrared polarization image fusion aims to generate a single image that integrates complementary information from both modalities to enhance scene perception. However, this task is hindered by significant modality gaps, high noise levels in polarization images, and the difficulty of preserving fine details from both sources. To address these challenges, we propose an end-to-end network, the feature-decoupled multi-scale Swin transformer (FDMSFuse). The proposed network uses a multi-scale architecture to capture rich shallow features. Its core component, the mix Swin transformer layer, employs a symmetric shared-key-value attention mechanism for efficient cross-modal interaction. Furthermore, a feature decoupling loss based on a channel-correlation matrix promotes feature complementarity while the DySample module ensures high-quality detail reconstruction. Experiments on the public LDDRS dataset demonstrate that FDMSFuse significantly outperforms nine state-of-the-art methods, ranking first on seven of nine key metrics. Crucially, it improves normalized mutual information (NMI) by nearly 25% over the runner-up, while also achieving top scores for visual fidelity (VIF) and perceived aesthetic quality (NIMA). Qualitative results further confirm its superior performance in noise suppression, texture preservation, and small-target enhancement.

Infrared small target detection (ISTD) plays a crucial role in many real-world applications. However, this task remains highly challenging due to the extremely small target size, low contrast, and complex background interference as infrared small targets often occupy fewer than 80 pixels in a $256\times 256$ image under a commonly used ISTD criterion. Although Segment Anything Model (SAM) shows strong generalization in image segmentation, directly applying SAM to ISTD is suboptimal, primarily due to the significant modality gap between RGB and infrared imagery, as well as the prohibitive cost of full-parameter fine-tuning. To address these challenges, we propose a prompt-free and parameter-efficient fine-tuning framework that adapts SAM for ISTD. To bridge the cross-modality gap while preserving the pretrained prior knowledge of SAM, a lightweight Infrared Adapter (IR-Adapter) is introduced into the image encoder, enabling effective task adaptation with only a small number of trainable parameters. Furthermore, to alleviate the loss of small target information in deep network layers, we design a Multi-Scale Feature Fusion (MSF) module that integrates hierarchical features from different encoder stages. In addition, a Coarse-to-Fine Head (CFH) with dual-branch prediction is proposed to incorporate fine-grained details for more accurate target localization and segmentation. Extensive experiments conducted on two public datasets demonstrate that the proposed method achieves better overall performance than existing representative approaches, yielding higher IoU, nIoU and Pd.

Infrared division-of-focal-plane (DoFP) polarization detectors often exhibit pronounced nonlinear response characteristics that cannot be effectively handled by existing nonuniformity correction algorithms. In this paper, we first establish an imaging model for infrared DoFP polarization detectors. To satisfy the requirements of infrared nonlinear DoFP polarization detectors, a model heterogeneity (MHE) nonuniformity correction algorithm is proposed. The proposed method constructs a mapping between the nonlinear response and a linear correction model, enabling effective suppression of nonuniformity noise while compensating for the correction-induced impact on polarization information. Experimental results demonstrate that the MHE algorithm significantly outperforms comparison methods in polarization preservation, nonuniformity noise suppression, and real-image correction. Compared with the comparison algorithms, the RMSE is substantially reduced. Meanwhile, the PCM is reduced from 70.1–278.4 to 14.8, while the APMR is improved from 16.9–22.8 to 33.9.