High-Dimensional Noise to Low-Dimensional Manifolds: A Manifold-Space Diffusion Framework for Degraded Hyperspectral Image Classification

• URL: http://arxiv.org/abs/2604.26279v1
• Date: Wed, 29 Apr 2026 04:20:42 GMT
• Title: High-Dimensional Noise to Low-Dimensional Manifolds: A Manifold-Space Diffusion Framework for Degraded Hyperspectral Image Classification
• Abstract summary: In real-world remote sensing scenarios, the superposition of multiple degradation factors disrupts intrinsic manifold structure.<n>This paper proposes a manifold-space diffusion framework (MSDiff) for robust hyperspectral classification under complex degradation conditions.
• Score: 14.798241863302438
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, Hyperspectral Image (HSI) classification has attracted increasing attention in remote sensing. However, HSI data are inherently high-dimensional but low-rank, with discriminative information concentrated on a low-dimensional latent manifold. In real-world remote sensing scenarios, the superposition of multiple degradation factors disrupts this intrinsic manifold structure, driving samples away from their original low-dimensional distribution and introducing substantial redundant and non-discriminative variations. To better handle this challenge, this paper proposes a manifold-space diffusion framework (MSDiff) for robust hyperspectral classification under complex degradation conditions. Specifically, the proposed method first maps high-dimensional, degradation-affected HSI data into a compact low-dimensional manifold through a discriminative spectral-spatial reconstruction task, preserving class semantics and reducing redundant variations. A diffusion-based generative model is then applied to regularize the spectral-spatial distribution within the manifold, enabling progressive refinement and stabilization of latent features against residual degradations. The key advantage of the proposed framework lies in performing diffusion-based distribution modeling directly on the low-dimensional manifold, effectively decoupling degradation-induced disturbances from intrinsic discriminative structures and enhancing representation stability under complex degradations. Experimental results on multiple hyperspectral benchmarks demonstrate consistent performance improvements over state-of-the-art methods under diverse composite degradation settings. The code will be available at https://github.com/yangboxiang1207/MSDiff

Related papers

• Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection [58.25418970608328]
  We study Single-Domain Generalized Object Detection (Single-DGOD), which aims to transfer a detector trained on a single source domain to multiple unseen domains.<n>Existing methods mainly rely on simulation-driven strategies, such as data augmentation or textual prompts, to enlarge the training distribution.<n>We propose Manifold Regression with Visual-Text Dual Chain-of-Thought (MR-DCoT), which formulates unknown-domain generalization as a manifold regression problem.
  arXiv  Detail & Related papers  (2026-07-08T09:27:15Z)
• Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine [60.669081685261965]
  Diffusion models generate high-dimensional data with remarkable quality.<n>How their training efficiently learns the score function remains theoretically unexplained.<n>We instantiate this principle as Score-induced Latent Diffusion (SiLD)
  arXiv  Detail & Related papers  (2026-05-16T16:51:10Z)
• DegBins: Degradation-Driven Binning for Depth Super-Resolution [57.61783461543096]
  DegBins is a novel DSR framework that leverages degradation-driven binning to adaptively enhance residual modeling.<n>DegBins consistently outperforms existing state-of-the-art methods in terms of accuracy, robustness, and generalization.
  arXiv  Detail & Related papers  (2026-05-10T16:17:11Z)
• Better with Less: Tackling Heterogeneous Multi-Modal Image Joint Pretraining via Conditioned and Degraded Masked Autoencoder [34.73963627819185]
  High-resolution (HR) joint optical and synthetic aperture radar (SAR) pretraining seeks modality synergy to mutually enhance single-source representations.<n>We propose CoDe-MAE, pioneering a textitbetter synergy with less alignment philosophy.<n>CoDe-MAE successfully prevents representation degradation and establishes new state-of-the-art performance across diverse single- and bi-modal downstream tasks.
  arXiv  Detail & Related papers  (2026-04-18T10:23:00Z)
• Single Image Super-Resolution via Bivariate `A Trous Wavelet Diffusion [5.897882149801945]
  Super resolution (SR) models need to be able to recover high frequency structure without introducing artifacts.<n>We introduce BATDiff, which provides structured cross scale guidance during the generative process.<n>It produces sharper and more structurally consistent reconstructions than existing diffusion and non diffusion baselines.
  arXiv  Detail & Related papers  (2026-03-07T14:36:37Z)
• Hyperspectral Super-Resolution with Inter-Image Variability via Degradation-based Low-Rank and Residual Fusion Method [2.317803962255901]
  Fusion of hyperspectral image with multispectral image (MSI) provides effective way to enhance spatial resolution of HSI.<n>Due to different acquisition conditions, there may exist spectral variability and spatially localized changes between HSI and MSI.<n>Existing methods typically handle inter-image variability applying direct transformations.<n>We propose a Degradation-based Low-Rank and Residual Fusion (DLRRF) model to address this challenge.
  arXiv  Detail & Related papers  (2025-11-19T02:45:31Z)
• Spectral-Spatial Extraction through Layered Tensor Decomposition for Hyperspectral Anomaly Detection [6.292153194561472]
  Low rank tensor representation (LRTR) methods are very useful for hyperspectral anomaly detection (HAD)<n>We first apply non-negative matrix factorization (NMF) to alleviate spectral dimensionality redundancy and extract spectral anomaly.<n>We then employ LRTR to extract spatial anomaly while mitigating spatial redundancy, yielding a highly efffcient layered tensor decomposition framework for HAD.<n> Experimental results on the Airport-Beach-Urban and MVTec datasets demonstrate that our approach outperforms state-of-the-art methods in the HAD task.
  arXiv  Detail & Related papers  (2025-03-07T07:08:14Z)
• Irregular Tensor Low-Rank Representation for Hyperspectral Image Representation [71.69331824668954]
  Spectral variations pose a common challenge in analyzing hyperspectral images (HSI)<n>Low-rank tensor representation has emerged as a robust strategy, leveraging inherent correlations within HSI data.<n>We propose a novel model for irregular tensor lowrank representation tailored to efficiently model irregular 3D cubes.
  arXiv  Detail & Related papers  (2024-10-24T02:56:22Z)
• Physics-Inspired Degradation Models for Hyperspectral Image Fusion [61.743696362028246]
  Most fusion methods solely focus on the fusion algorithm itself and overlook the degradation models. We propose physics-inspired degradation models (PIDM) to model the degradation of LR-HSI and HR-MSI. Our proposed PIDM can boost the fusion performance of existing fusion methods in practical scenarios.
  arXiv  Detail & Related papers  (2024-02-04T09:07:28Z)
• DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration [103.79030498369319]
  Self-supervised diffusion model for hyperspectral image restoration is proposed. textttDDS2M enjoys stronger ability to generalization compared to existing diffusion-based methods. Experiments on HSI denoising, noisy HSI completion and super-resolution on a variety of HSIs demonstrate textttDDS2M's superiority over the existing task-specific state-of-the-arts.
  arXiv  Detail & Related papers  (2023-03-12T14:57:04Z)
• Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration [66.68541690283068]
  We propose a unified paradigm combining the spatial and spectral properties for hyperspectral image restoration. The proposed paradigm enjoys performance superiority from the non-local spatial denoising and light computation complexity. Experiments on HSI denoising, compressed reconstruction, and inpainting tasks, with both simulated and real datasets, demonstrate its superiority.
  arXiv  Detail & Related papers  (2020-10-24T15:53:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.