Progressive Flow-inspired Unfolding for Spectral Compressive Imaging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908539925037056 |
|---|---|
| author | Wang, Xiaodong Wang, Ping He, Zijun Qin, Mengjie Yuan, Xin |
| author_facet | Wang, Xiaodong Wang, Ping He, Zijun Qin, Mengjie Yuan, Xin |
| contents | Coded aperture snapshot spectral imaging (CASSI) retrieves a 3D hyperspectral image (HSI) from a single 2D compressed measurement, which is a highly challenging reconstruction task. Recent deep unfolding networks (DUNs), empowered by explicit data-fidelity updates and implicit deep denoisers, have achieved the state of the art in CASSI reconstruction. However, existing unfolding approaches suffer from uncontrollable reconstruction trajectories, leading to abrupt quality jumps and non-gradual refinement across stages. Inspired by diffusion trajectories and flow matching, we propose a novel trajectory-controllable unfolding framework that enforces smooth, continuous optimization paths from noisy initial estimates to high-quality reconstructions. To achieve computational efficiency, we design an efficient spatial-spectral Transformer tailored for hyperspectral reconstruction, along with a frequency-domain fusion module to gurantee feature consistency. Experiments on simulation and real data demonstrate that our method achieves better reconstruction quality and efficiency than prior state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12079 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Progressive Flow-inspired Unfolding for Spectral Compressive Imaging Wang, Xiaodong Wang, Ping He, Zijun Qin, Mengjie Yuan, Xin Computer Vision and Pattern Recognition Coded aperture snapshot spectral imaging (CASSI) retrieves a 3D hyperspectral image (HSI) from a single 2D compressed measurement, which is a highly challenging reconstruction task. Recent deep unfolding networks (DUNs), empowered by explicit data-fidelity updates and implicit deep denoisers, have achieved the state of the art in CASSI reconstruction. However, existing unfolding approaches suffer from uncontrollable reconstruction trajectories, leading to abrupt quality jumps and non-gradual refinement across stages. Inspired by diffusion trajectories and flow matching, we propose a novel trajectory-controllable unfolding framework that enforces smooth, continuous optimization paths from noisy initial estimates to high-quality reconstructions. To achieve computational efficiency, we design an efficient spatial-spectral Transformer tailored for hyperspectral reconstruction, along with a frequency-domain fusion module to gurantee feature consistency. Experiments on simulation and real data demonstrate that our method achieves better reconstruction quality and efficiency than prior state-of-the-art approaches. |
| title | Progressive Flow-inspired Unfolding for Spectral Compressive Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.12079 |