Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.27653 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913076429717504 |
|---|---|
| author | Gao, Dahua Dong, Yubo Li, Anqi Lin, Zhenyuan Gao, Ang Liu, Danhua Shi, Guangming |
| author_facet | Gao, Dahua Dong, Yubo Li, Anqi Lin, Zhenyuan Gao, Ang Liu, Danhua Shi, Guangming |
| contents | Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectral imaging enables instantaneous hyperspectral images (HSIs) capture, making real-time object detection feasible, yet its potential is often compromised by time-consuming post-capture reconstruction. To address this issue, we propose the Focal U-shaped Network (FUN), a novel end-to-end framework that jointly performs HSI reconstruction and object detection via multi-task learning. FUN employs a shared U-shaped backbone, where reconstruction provides underlying spectral information while detection guides semantic-aware priors learning, facilitating mutually beneficial task interaction. Crucially, we introduce focal modulation, an efficient alternative to self-attention that modulates spatial and spectral features while reducing quadratic computational complexity, enabling a self-attention-free architecture for joint reconstruction and detection. Furthermore, we contribute a new HSI object detection dataset with 8712 annotated objects across 363 HSIs to facilitate evaluation of the proposed method. Experiments demonstrate that FUN achieves state-of-the-art performance on both tasks, using 40% fewer parameters and 30% less computation than recent alternatives, making it promising for future real-time edge deployment. The code and datasets are available: https://github.com/ShawnDong98/FUN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27653 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging Gao, Dahua Dong, Yubo Li, Anqi Lin, Zhenyuan Gao, Ang Liu, Danhua Shi, Guangming Computer Vision and Pattern Recognition Conventional push-broom hyperspectral imaging suffers from slow acquisition speeds, precluding real-time object detection; in contrast, snapshot spectral imaging enables instantaneous hyperspectral images (HSIs) capture, making real-time object detection feasible, yet its potential is often compromised by time-consuming post-capture reconstruction. To address this issue, we propose the Focal U-shaped Network (FUN), a novel end-to-end framework that jointly performs HSI reconstruction and object detection via multi-task learning. FUN employs a shared U-shaped backbone, where reconstruction provides underlying spectral information while detection guides semantic-aware priors learning, facilitating mutually beneficial task interaction. Crucially, we introduce focal modulation, an efficient alternative to self-attention that modulates spatial and spectral features while reducing quadratic computational complexity, enabling a self-attention-free architecture for joint reconstruction and detection. Furthermore, we contribute a new HSI object detection dataset with 8712 annotated objects across 363 HSIs to facilitate evaluation of the proposed method. Experiments demonstrate that FUN achieves state-of-the-art performance on both tasks, using 40% fewer parameters and 30% less computation than recent alternatives, making it promising for future real-time edge deployment. The code and datasets are available: https://github.com/ShawnDong98/FUN. |
| title | FUN: A Focal U-Net Combining Reconstruction and Object Detection for Snapshot Spectral Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.27653 |