{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ressr-a-residual-approach-to-super-resolving","title":"ResSR: A Computationally Efficient Residual Approach to Super-Resolving Multispectral Images","arxiv_id":"2408.13225","date":"2024-08-23","proceeding":null,"authors":["Haley Duba-Sullivan","Emma J. Reid","Sophie Voisin","Charles A. Bouman","Gregery T. Buzzard"],"abstract":"Multispectral imaging sensors typically have wavelength-dependent resolution, which limits downstream processing. Consequently, researchers have proposed multispectral image super-resolution (MSI-SR) methods which upsample low-resolution bands to achieve a common resolution across all wavelengths. However, existing MSI-SR methods are computationally expensive because they require spatially regularized deconvolution and/or training-based methods. In this paper, we introduce ResSR, a computationally efficient MSI-SR method that achieves high-quality reconstructions by using spectral decomposition along with spatial residual correction. ResSR applies singular value decomposition to identify correlations across spectral bands, uses pixel-wise computation to upsample the MSI, and then applies a residual correction process to correct the high-spatial frequency components of the upsampled bands. While ResSR is formulated as the solution to a spatially-coupled optimization problem, we use pixel-wise regularization and derive an approximate non-iterative solution, resulting in a computationally efficient, non-iterative algorithm. Results on a combination of simulated and measured data show that ResSR is 2$\\times$ to 10$\\times$ faster than alternative MSI-SR algorithms, while producing comparable or better image quality. Code is available at https://github.com/hdsullivan/ResSR.","url_abs":"https://arxiv.org/abs/2408.13225v2","url_pdf":"https://arxiv.org/pdf/2408.13225v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ressr-a-residual-approach-to-super-resolving","repo_url":"https://github.com/hdsullivan/ressr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"multispectral-image-super-resolution","task_name":"Multispectral Image Super-resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}