In2SET: Intra-Inter Similarity Exploiting Transformer for Dual-Camera Compressive Hyperspectral Imaging
This work addresses snapshot hyperspectral imaging for practical applications, offering an incremental improvement over existing dual-camera compressive hyperspectral imaging methods.
The paper tackles the problem of reconstructing 3D hyperspectral images from dual-camera compressive data by introducing In2SET, a transformer-based network that leverages panchromatic image intra-similarity and feature alignment, resulting in improved spatial-spectral fidelity and outperforming state-of-the-art methods in reconstruction quality and computational complexity.
Dual-Camera Compressed Hyperspectral Imaging (DCCHI) offers the capability to reconstruct 3D Hyperspectral Image (HSI) by fusing compressive and Panchromatic (PAN) image, which has shown great potential for snapshot hyperspectral imaging in practice. In this paper, we introduce a novel DCCHI reconstruction network, the Intra-Inter Similarity Exploiting Transformer (In2SET). Our key insight is to make full use of the PAN image to assist the reconstruction. To this end, we propose using the intra-similarity within the PAN image as a proxy for approximating the intra-similarity in the original HSI, thereby offering an enhanced content prior for more accurate HSI reconstruction. Furthermore, we aim to align the features from the underlying HSI with those of the PAN image, maintaining semantic consistency and introducing new contextual information for the reconstruction process. By integrating In2SET into a PAN-guided unrolling framework, our method substantially enhances the spatial-spectral fidelity and detail of the reconstructed images, providing a more comprehensive and accurate depiction of the scene. Extensive experiments conducted on both real and simulated datasets demonstrate that our approach consistently outperforms existing state-of-the-art methods in terms of reconstruction quality and computational complexity. Code will be released.