Hyperspectral Image Denoising via L0 Regularized Low-Rank Tucker Decomposition

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING(2024)

引用 0|浏览1
暂无评分
摘要
This article studies the mixed noise removal problem for hyperspectral images (HSIs), which often suffer from Gaussian noise and sparse noise. Conventional denoising models mainly employ the L-1-norm-based regularizers to remove sparse noise and ensure piecewise smoothness. However, the denoising performance is poor for highly structured images with severe noise since the L-1 norm overpenalizes large entries. To tackle this limitation, we propose a denoising model that combines tensor decomposition with two kinds of L-0-norm-based regularizers. First, we use low-rank Tucker decomposition with the Stiefel manifold to characterize the global correlation of HSIs. Then, we utilize the L-0-norm to leverage the intrinsic sparsity information of the corruption domain, thereby enhancing the effectiveness of sparse noise removal. Simultaneously, we introduce a weighted L-0-norm regularizer on the gradient of each pixel to promote the local spectral-spatial smoothness. To solve the proposed model, we design a hard-thresholding-based alternating direction method of multipliers algorithm. Instead of spending time to find a proper rank in advance, we adopt a rank increasing scheme to dynamically adjust the tensor rank during the optimization procedure. In this way, our algorithm avoids the rank selection burden and improves computational efficiency. Finally, we test the proposed method on both synthetic and real datasets. Numerical results demonstrate its superiority, especially, the improvements of our method over the best-compared results up to 2.07 dB for mixed noise removal.
更多
查看译文
关键词
Low-rank,piecewise smooth,rank-increasing,sparse
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要