Physics-Driven Multispectral Filter Array Pattern Optimization and Hyperspectral Image Reconstruction
Pan Liu, Yongqiang Zhao, Kai Feng, Seong G. Kong
Abstract
This paper presents a hyperspectral image (HSI) reconstruction technique based on physics-driven optimization of multispectral filter array (MSFA) patterns. The encoding of HSIs using an MSFA and their decoding through deep learning has gained increasing attention. However, previous studies have seldom explored pattern optimization from a physical perspective during the encoding process. In this paper, we apply a spectral sensitivity function (SSF) response model to generate the MSFA, and the goal of encoder optimization extends from SSF to physical structural parameters. To fully utilize spatial and spectral information in the decoding process, we design an end-to-end dual-branch spatial-spectral fusion network (DSFNet). By jointly optimizing the MSFA with the SSF response model and DSFNet, the proposed method significantly improves the reconstruction accuracy of HSI. When compared with existing HSI reconstruction methods, our proposed approach achieves state-of-the-art performance in both metric and visual quality.