ISPDiff: Interpretable Scale-Propelled Diffusion Model for Hyperspectral Image Super-Resolution

高光谱成像 遥感 图像分辨率 比例(比率) 分辨率(逻辑) 扩散 人工智能 计算机科学 计算机视觉 地质学 地图学 物理 地理 热力学
作者
Wenqian Dong,Sen Liu,Song Xiao,Jiahui Qu,Yunsong Li
出处
期刊:IEEE Transactions on Geoscience and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:62: 1-14 被引量:2
标识
DOI:10.1109/tgrs.2024.3407967
摘要

Hyperspectral image (HSI) super-resolution (SR) employing the denoising diffusion probabilistic model (DDPM) holds significant promise with its remarkable performance. However, existing relevant works exhibit two limitations: i) Directly applying DDPM to fusion-based HSI SR (HSI-SR) ignores the physical mechanism of HSI-SR and unique characteristics of HSI, resulting in less interpretability; ii) Scale-invariant DDPM suffers from a time-consuming inference. To tackle these issues, we propose an interpretable scale-propelled diffusion model (ISPDiff) for HSI-SR, which combines the underlying principles of HSI-SR with DDPM for progressively unrolling reconstruction by learning its distribution at various scales, enhancing the transparency significantly and reducing the inference time prominently. Concretely, we destroy and downsample HSI into Gaussian noise in the forward process of ISPDiff. Then we design a unified scale-flexible model in the backward process to iteratively refine HSI in a coarse-to-fine manner through scale-matched reconstruction and cross-scale upsampling, which can be unfolded with optimization algorithms. These solved equations are one-to-one corresponding unrolled into two deep neural networks, called progressive perceptual model-driven scale-matched restoration network (P 2 MSRN) and cross-scale model-driven upsampling network (CMUN). Through end-to-end training, the proposed ISPDiff implements HSI-SR with a scale-propelled unrolling diffusion characterized by enhanced interpretability, stronger task orientation, and reduced time consumption. Systematic experiments have been conducted on three public datasets, demonstrating that ISPDiff outperforms state-of-the-art methods. Code is available at https://github.com/Jiahuiqu/ISPDiff.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
蜡笔小新完成签到 ,获得积分10
4秒前
li锂狸发布了新的文献求助10
7秒前
7秒前
DavidChen发布了新的文献求助10
7秒前
传奇3应助2032jia采纳,获得10
8秒前
科研通AI2S应助Anoxra采纳,获得10
9秒前
鸡蛋布丁完成签到 ,获得积分10
9秒前
10秒前
15秒前
16秒前
dhjskak发布了新的文献求助20
17秒前
17秒前
小高同学发布了新的文献求助10
20秒前
20秒前
稳重的若雁应助111采纳,获得10
21秒前
上官若男应助儒雅的冷梅采纳,获得10
22秒前
彭于晏应助喜欢也没用采纳,获得10
22秒前
畅跑daily完成签到,获得积分10
22秒前
谨慕轩发布了新的文献求助10
24秒前
酷波er应助典雅书翠采纳,获得10
24秒前
25秒前
Hello应助Shane采纳,获得10
25秒前
27秒前
苏卿应助orchid采纳,获得10
29秒前
31秒前
32秒前
32秒前
33秒前
知画春秋完成签到 ,获得积分10
34秒前
doby发布了新的文献求助10
34秒前
35秒前
冷静的仙人掌完成签到,获得积分10
35秒前
song完成签到,获得积分10
36秒前
36秒前
36秒前
Fiona发布了新的文献求助10
37秒前
38秒前
38秒前
高分求助中
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
Rechtsphilosophie 1000
Bayesian Models of Cognition:Reverse Engineering the Mind 888
Le dégorgement réflexe des Acridiens 800
Defense against predation 800
Very-high-order BVD Schemes Using β-variable THINC Method 568
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3136281
求助须知:如何正确求助?哪些是违规求助? 2787312
关于积分的说明 7780828
捐赠科研通 2443293
什么是DOI,文献DOI怎么找? 1299081
科研通“疑难数据库(出版商)”最低求助积分说明 625325
版权声明 600905