TY - JOUR
T1 - Transductive gradient injection for improved hyperspectral image denoising
AU - Bu, Yuanyang
AU - Zhao, Yongqiang
AU - Xue, Jize
AU - Kong, Seong G.
AU - Yao, Jiaxin
AU - Chan, Jonathan Cheung Wai
AU - Liu, Pan
AU - Zhang, Xun
N1 - Publisher Copyright:
© 2025 Elsevier Ltd
PY - 2025/3/1
Y1 - 2025/3/1
N2 - In real-world hyperspectral imaging, noise disproportionately affects specific spectral bands. However, existing denoising techniques struggle to discern the varied contributions of different signal-to-noise ratios across spectral bands, leading to suboptimal performance. To fill this gap, we propose a transductive gradient learning framework that utilizes high signal-to-noise ratio bands to guide the inference of gradient patterns in low signal-to-noise ratio bands, substantially enhancing denoising effectiveness. Unlike existing approaches that only recover global low-rank structures, our framework introduces a transductive gradient injection regularization term to capture both global low-rank and local sparse gradient patterns. This term combines a low-rank matrix for global patterns and a sparse matrix for local patterns, leveraging pre-learned feature matrices from high signal-to-noise ratio band gradients to accurately inject spatial gradient textures, avoid excessive singular value constraints, and achieve efficient noise separation. Additionally, we have developed an efficient alternating direction method of multipliers algorithm for optimization. Extensive synthetic and real experiments on hyperspectral image datasets, along with applications in remote sensing, highlight significant performance gains. Across all datasets and noise conditions, our method achieves an average improvement of nearly 33% in overall peak signal-to-noise ratio and a 23% increase in spectral angle mapper compared to state-of-the-art hyperspectral image denoising methods.
AB - In real-world hyperspectral imaging, noise disproportionately affects specific spectral bands. However, existing denoising techniques struggle to discern the varied contributions of different signal-to-noise ratios across spectral bands, leading to suboptimal performance. To fill this gap, we propose a transductive gradient learning framework that utilizes high signal-to-noise ratio bands to guide the inference of gradient patterns in low signal-to-noise ratio bands, substantially enhancing denoising effectiveness. Unlike existing approaches that only recover global low-rank structures, our framework introduces a transductive gradient injection regularization term to capture both global low-rank and local sparse gradient patterns. This term combines a low-rank matrix for global patterns and a sparse matrix for local patterns, leveraging pre-learned feature matrices from high signal-to-noise ratio band gradients to accurately inject spatial gradient textures, avoid excessive singular value constraints, and achieve efficient noise separation. Additionally, we have developed an efficient alternating direction method of multipliers algorithm for optimization. Extensive synthetic and real experiments on hyperspectral image datasets, along with applications in remote sensing, highlight significant performance gains. Across all datasets and noise conditions, our method achieves an average improvement of nearly 33% in overall peak signal-to-noise ratio and a 23% increase in spectral angle mapper compared to state-of-the-art hyperspectral image denoising methods.
KW - Hyperspectral imaging
KW - Mixture noise removal
KW - Total variation
KW - Transductive learning
UR - http://www.scopus.com/inward/record.url?scp=85214337000&partnerID=8YFLogxK
U2 - 10.1016/j.engappai.2024.109973
DO - 10.1016/j.engappai.2024.109973
M3 - 文章
AN - SCOPUS:85214337000
SN - 0952-1976
VL - 143
JO - Engineering Applications of Artificial Intelligence
JF - Engineering Applications of Artificial Intelligence
M1 - 109973
ER -