Answers are grounded in this paper and cite their sources.
Stripe noise in remote sensing images, often caused by inconsistent sensor responses and dark current, significantly degrades image quality and complicates analysis. Existing methods are effective for regular stripe patterns, but they often rely on simplified statistical assumptions, fixed smoothness constraints, or global sparsity priors, making it difficult to simultaneously preserve structural details and characterize spatially varying stripe components in real remote sensing images. To address this, we propose a variational destriping framework integrating statistical feature constraints. A location-aware stripe variational filtering estimates statistical guidance, which is embedded into a two-dimensional variational model.An adaptive Huber-enhanced anisotropic total variation (TV) regularization suppresses staircase artifacts while preserving edges, and reweighted block sparsity captures the spatially varying sparsity of real stripe noise. The model is optimized using iterative reweighted least squares and the alternating direction method of multipliers. Experiments on simulated and real datasets demonstrate superior stripe removal and detail preservation compared to state-of-the-art approaches.
No takes yet. Share an insight, caveat, or question.
Wu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: