A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Jianjun, Wu, Zebin, Xiao, Liang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917771027152896
author Liu, Jianjun
Wu, Zebin
Xiao, Liang
author_facet Liu, Jianjun
Wu, Zebin
Xiao, Liang
contents Fusion-based hyperspectral image (HSI) super-resolution aims to produce a high-spatial-resolution HSI by fusing a low-spatial-resolution HSI and a high-spatial-resolution multispectral image. Such a HSI super-resolution process can be modeled as an inverse problem, where the prior knowledge is essential for obtaining the desired solution. Motivated by the success of diffusion models, we propose a novel spectral diffusion prior for fusion-based HSI super-resolution. Specifically, we first investigate the spectrum generation problem and design a spectral diffusion model to model the spectral data distribution. Then, in the framework of maximum a posteriori, we keep the transition information between every two neighboring states during the reverse generative process, and thereby embed the knowledge of trained spectral diffusion model into the fusion problem in the form of a regularization term. At last, we treat each generation step of the final optimization problem as its subproblem, and employ the Adam to solve these subproblems in a reverse sequence. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach. The code of the proposed approach will be available on https://github.com/liuofficial/SDP.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08955
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution
Liu, Jianjun
Wu, Zebin
Xiao, Liang
Computer Vision and Pattern Recognition
Image and Video Processing
Fusion-based hyperspectral image (HSI) super-resolution aims to produce a high-spatial-resolution HSI by fusing a low-spatial-resolution HSI and a high-spatial-resolution multispectral image. Such a HSI super-resolution process can be modeled as an inverse problem, where the prior knowledge is essential for obtaining the desired solution. Motivated by the success of diffusion models, we propose a novel spectral diffusion prior for fusion-based HSI super-resolution. Specifically, we first investigate the spectrum generation problem and design a spectral diffusion model to model the spectral data distribution. Then, in the framework of maximum a posteriori, we keep the transition information between every two neighboring states during the reverse generative process, and thereby embed the knowledge of trained spectral diffusion model into the fusion problem in the form of a regularization term. At last, we treat each generation step of the final optimization problem as its subproblem, and employ the Adam to solve these subproblems in a reverse sequence. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach. The code of the proposed approach will be available on https://github.com/liuofficial/SDP.
title A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2311.08955