THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915440188456960 |
|---|---|
| author | Jin, Hongkun Jiang, Hongcheng Zhang, Zejun Zhang, Yuan Fu, Jia Li, Tingfeng Luo, Kai |
| author_facet | Jin, Hongkun Jiang, Hongcheng Zhang, Zejun Zhang, Yuan Fu, Jia Li, Tingfeng Luo, Kai |
| contents | Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale feature modeling. Hyperspectral images exhibit intrinsic spectral priors (e.g., abundance sparsity) and spatial priors (e.g., non-local similarity), which are critical for accurate reconstruction. From a spectral-spatial perspective, Vision Transformers (ViTs) face two major limitations: they struggle to preserve high-frequency components--such as material edges and texture transitions--and suffer from attention dispersion across redundant tokens. These issues stem from the global self-attention mechanism, which tends to dilute high-frequency signals and overlook localized details. To address these challenges, we propose the Token-wise High-frequency Augmentation Transformer (THAT), a novel framework designed to enhance hyperspectral pansharpening through improved high-frequency feature representation and token selection. Specifically, THAT introduces: (1) Pivotal Token Selective Attention (PTSA) to prioritize informative tokens and suppress redundancy; (2) a Multi-level Variance-aware Feed-forward Network (MVFN) to enhance high-frequency detail learning. Experiments on standard benchmarks show that THAT achieves state-of-the-art performance with improved reconstruction quality and efficiency. The source code is available at https://github.com/kailuo93/THAT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08183 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening Jin, Hongkun Jiang, Hongcheng Zhang, Zejun Zhang, Yuan Fu, Jia Li, Tingfeng Luo, Kai Computer Vision and Pattern Recognition Image and Video Processing Transformer-based methods have demonstrated strong potential in hyperspectral pansharpening by modeling long-range dependencies. However, their effectiveness is often limited by redundant token representations and a lack of multi-scale feature modeling. Hyperspectral images exhibit intrinsic spectral priors (e.g., abundance sparsity) and spatial priors (e.g., non-local similarity), which are critical for accurate reconstruction. From a spectral-spatial perspective, Vision Transformers (ViTs) face two major limitations: they struggle to preserve high-frequency components--such as material edges and texture transitions--and suffer from attention dispersion across redundant tokens. These issues stem from the global self-attention mechanism, which tends to dilute high-frequency signals and overlook localized details. To address these challenges, we propose the Token-wise High-frequency Augmentation Transformer (THAT), a novel framework designed to enhance hyperspectral pansharpening through improved high-frequency feature representation and token selection. Specifically, THAT introduces: (1) Pivotal Token Selective Attention (PTSA) to prioritize informative tokens and suppress redundancy; (2) a Multi-level Variance-aware Feed-forward Network (MVFN) to enhance high-frequency detail learning. Experiments on standard benchmarks show that THAT achieves state-of-the-art performance with improved reconstruction quality and efficiency. The source code is available at https://github.com/kailuo93/THAT. |
| title | THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2508.08183 |