Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yunshan, Gong, Wenwu, Wang, Qianqian, Wang, Chao, Yang, Lili
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.16735
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912442352664576
author Li, Yunshan
Gong, Wenwu
Wang, Qianqian
Wang, Chao
Yang, Lili
author_facet Li, Yunshan
Gong, Wenwu
Wang, Qianqian
Wang, Chao
Yang, Lili
contents Recent approaches based on transform-based tensor nuclear norm (TNN) have demonstrated notable effectiveness in hyperspectral image (HSI) inpainting by leveraging low-rank structures in latent representations. Recent developments incorporate deep transforms to improve low-rank tensor representation; however, existing approaches typically restrict the transform to the spectral mode, neglecting low-rank properties along other tensor modes. In this paper, we propose a novel 3-directional deep low-rank tensor representation (3DeepRep) model, which performs deep nonlinear transforms along all three modes of the HSI tensor. To enforce low-rankness, the model minimizes the nuclear norms of mode-i frontal slices in the corresponding latent space for each direction (i=1,2,3), forming a 3-directional TNN regularization. The outputs from the three directional branches are subsequently fused via a learnable aggregation module to produce the final result. An efficient gradient-based optimization algorithm is developed to solve the model in a self-supervised manner. Extensive experiments on real-world HSI datasets demonstrate that the proposed method achieves superior inpainting performance compared to existing state-of-the-art techniques, both qualitatively and quantitatively.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16735
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 3DeepRep: 3D Deep Low-rank Tensor Representation for Hyperspectral Image Inpainting
Li, Yunshan
Gong, Wenwu
Wang, Qianqian
Wang, Chao
Yang, Lili
Computer Vision and Pattern Recognition
Image and Video Processing
Recent approaches based on transform-based tensor nuclear norm (TNN) have demonstrated notable effectiveness in hyperspectral image (HSI) inpainting by leveraging low-rank structures in latent representations. Recent developments incorporate deep transforms to improve low-rank tensor representation; however, existing approaches typically restrict the transform to the spectral mode, neglecting low-rank properties along other tensor modes. In this paper, we propose a novel 3-directional deep low-rank tensor representation (3DeepRep) model, which performs deep nonlinear transforms along all three modes of the HSI tensor. To enforce low-rankness, the model minimizes the nuclear norms of mode-i frontal slices in the corresponding latent space for each direction (i=1,2,3), forming a 3-directional TNN regularization. The outputs from the three directional branches are subsequently fused via a learnable aggregation module to produce the final result. An efficient gradient-based optimization algorithm is developed to solve the model in a self-supervised manner. Extensive experiments on real-world HSI datasets demonstrate that the proposed method achieves superior inpainting performance compared to existing state-of-the-art techniques, both qualitatively and quantitatively.
title 3DeepRep: 3D Deep Low-rank Tensor Representation for Hyperspectral Image Inpainting
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2506.16735