paper-with-me

홈 › Papers

HIR-Diff: Unsupervised Hyperspectral Image Restoration Via Improved Diffusion Models

2024-02-24 · CVPR 2024 1 · Li Pang, Xiangyu Rui, Long Cui, Hongzhong Wang, Deyu Meng, Xiangyong Cao

Hyperspectral image (HSI) restoration aims at recovering clean images from degraded observations and plays a vital role in downstream tasks. Existing model-based methods have limitations in accurately modeling the complex image characteristics with handcraft priors, and deep learning-based methods suffer from poor generalization ability. To alleviate these issues, this paper proposes an unsupervised HSI restoration framework with pre-trained diffusion model (HIR-Diff), which restores the clean HSIs from the product of two low-rank components, i.e., the reduced image and the coefficient matrix. Specifically, the reduced image, which has a low spectral dimension, lies in the image field and can be inferred from our improved diffusion model where a new guidance function with total variation (TV) prior is designed to ensure that the reduced image can be well sampled. The coefficient matrix can be effectively pre-estimated based on singular value decomposition (SVD) and rank-revealing QR (RRQR) factorization. Furthermore, a novel exponential noise schedule is proposed to accelerate the restoration process (about 5$\times$ acceleration for denoising) with little performance decrease. Extensive experimental results validate the superiority of our method in both performance and speed on a variety of HSI restoration tasks, including HSI denoising, noisy HSI super-resolution, and noisy HSI inpainting. The code is available at https://github.com/LiPang/HIRDiff.

📄 PDF Abstract BibTeX arXiv:2402.15865

Code (1)

lipang/hirdiff 공식 구현 pytorch

Tasks

DenoisingImage RestorationSuper-Resolution

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

SHARE: A Fully Unsupervised Framework for Single Hyperspectral Image Restoration

2026-01-20 · Jiangwei Xie, Zhang Wen, Mike Davies, Dongdong Chen arxiv

Hyperspectral image (HSI) restoration is a fundamental challenge in computational imaging and computer vision. It involves ill-posed inverse problems, such as inpainting and super-resolution. Although deep learning metho…

Image Restoration

Self-supervised Hyperspectral Image Restoration using Separable Image Prior

2019-07-01 · Ryuji Imamura, Tatsuki Itasaka, Masahiro Okuda

Supervised learning with a convolutional neural network is recognized as a powerful means of image restoration. However, most such methods have been designed for application to grayscale and/or color images; therefore, t…

DenoisingImage RestorationSelf-Supervised Learning

Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration

2016-06-01 · CVPR 2016 6 · Ying Fu, Yinqiang Zheng, Imari Sato, Yoichi Sato

Conventional scanning and multiplexing techniques for hyperspectral imaging suffer from limited temporal and/or spatial resolution. To resolve this issue, coding techniques are becoming increasingly popular in developing…

Image Restoration

HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation

2026-05-13 · Li Pang, Heng Zhao, Yijia Zhang, Deyu Meng 외 arxiv

Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real-world HSIs suffer from noise, blur, and resolution loss. However, existing models trained on source data often fail on target domains lackin…

Image Restoration

Leveraging pretrained RGB denoisers for hyperspectral image restoration

2026-05-23 · Daniele Picone, Mohamad Jouni, Mauro Dalla-Mura arxiv

Hyperspectral image restoration faces several challenges, including limited training data, strong sensor specificity, and high spectral dimensionality. These limitations hinder the learning of robust hyperspectral priors…

Image Restoration