Answers are grounded in this paper and cite their sources.
Compressive sensing (CS) is essential for achieving high-resolution polarimetric inverse synthetic aperture radar (ISAR) imaging. However, conventional sparse recovery paradigms primarily rely on independent single-channel processing, thereby neglecting inherent cross-polarization correlations. To address this issue, this article proposes a full-polarimetric ISAR imaging algorithm via complex-valued multitask compressive sensing with a Laplacian scale mixture prior (CMTCS-LSM). CMTCS-LSM effectively leverages the structural dependencies by means of joint sparsity across multiple polarization channels. By deriving a probabilistic joint sparsity profile directly from the learned shared hyperparameters of the algorithm, the proposed method establishes an intrinsic variance fusion mechanism that avoids heuristic polarimetric pseudocolor synthesis. Extensive experiments evaluate the robustness of the algorithm under nonideal scenarios. Specifically, under low signal-to-noise ratio and substantial data scarcity conditions, CMTCS-LSM consistently maintains high peak signal-to-noise ratio and structural similarity index metrics, quantitatively demonstrating its capability to suppress background artifacts and preserve the morphological features.
No takes yet. Share an insight, caveat, or question.
Deng et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: