Progressive Flow-inspired Unfolding for Spectral Compressive Imaging
This work addresses the problem of abrupt quality jumps in hyperspectral image reconstruction for imaging applications, offering an incremental improvement over existing deep unfolding networks.
The paper tackles the challenging reconstruction of 3D hyperspectral images from 2D compressed measurements in coded aperture snapshot spectral imaging (CASSI) by proposing a trajectory-controllable unfolding framework, resulting in better reconstruction quality and efficiency than prior state-of-the-art methods.
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.