High-resolution Hyperspectral Imaging via Matrix Factorization
presented in CVPR 2011
Rei Kawakami, John Wright, Yu-Wing Tai, Yasuyuki Matsushita, Moshe Ben-Ezra, and Katsushi Ikeuchi
| Hyperspectral imaging is a promising tool for applications in geosensing, cultural heritage and beyond. However, compared to current RGB cameras, existing hyperspectral cameras are severely limited in spatial resolution. In this paper, we introduce a simple new technique for reconstructing a very high-resolution hyperspectral image from two readily obtained measurements: A lower-resolution hyperspectral image and a high-resolution RGB image. Our approach is divided into two stages: We first apply an unmixing algorithm to the hyperspectral input, to estimate a basis representing reflectance spectra. We then use this representation in conjunction with the RGB input to produce the desired result. Our approach to unmixing is motivated by the spatial sparsity of the hyperspectral input, and casts the unmixing problem as the search for a factorization of the input into a basis and a set of maximally sparse coefficients. Experiments show that this simple approach performs reasonably well on both simulations and real data examples. | |
| Paper (7.5MB) | |
| Code (100MB) new! | |
| Supplementary material 1 (0.16MB): Factorization algorithm details | |
| Supplementary material 2 (26MB): More experimental results | |
| Poster (11.8MB) | |
| Video (48MB) | |
| Slides in the video (4.7MB) | |
| Bibtex |
