Saved in:
Bibliographic Details
Main Authors: Xiang, Jijun, Wang, Tao, Wang, Jiayi, Wang, Pengxiang, Chen, Cheng, Wang, Nian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.11390
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910127400943616
author Xiang, Jijun
Wang, Tao
Wang, Jiayi
Wang, Pengxiang
Chen, Cheng
Wang, Nian
author_facet Xiang, Jijun
Wang, Tao
Wang, Jiayi
Wang, Pengxiang
Chen, Cheng
Wang, Nian
contents While Hyperspectral Anomaly Detection (HAD) excels at identifying sparse targets in complex scenes, existing models remain trapped in a scalar "reconstruction-as-endpoint" paradigm. This reliance on ambiguous scalar residuals consistently triggers sub-pixel anomaly vanishing during spatial downsampling, alongside severe confirmation bias when unpurified anomalies corrupt training weights. In this paper, we propose Reconstruction-to-Vector Diffusion (R2VD), which fundamentally redefines reconstruction as a manifold purification origin to establish a novel residual-guided generative dynamics paradigm. Our framework introduces a four-stage pipeline: (1) a Physical Prior Extraction (PPE) stage that mitigates early confirmation bias via dual-stream statistical guidance; (2) a Guided Manifold Purification (GMP) stage utilizing an OmniContext Autoencoder (OCA) to extract purified residual maps while preserving fragile sub-pixel topologies; (3) a Residual Score Modeling (RSM) stage where a Diffusion Transformer (DiT), guarded by a Physical Spectral Firewall (PSF), effectively isolates cross-spectral leakage; and (4) a Vector Dynamics Inference (VDI) stage that robustly decouples targets from backgrounds by evaluating high-dimensional vector interference patterns instead of conventional scalar errors. Comprehensive evaluations on eight datasets confirm that R2VD establishes a new state-of-the-art, delivering exceptional target detectability and background suppression. The code is available at https://github.com/Bondojijun/R2VD.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11390
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection
Xiang, Jijun
Wang, Tao
Wang, Jiayi
Wang, Pengxiang
Chen, Cheng
Wang, Nian
Computer Vision and Pattern Recognition
While Hyperspectral Anomaly Detection (HAD) excels at identifying sparse targets in complex scenes, existing models remain trapped in a scalar "reconstruction-as-endpoint" paradigm. This reliance on ambiguous scalar residuals consistently triggers sub-pixel anomaly vanishing during spatial downsampling, alongside severe confirmation bias when unpurified anomalies corrupt training weights. In this paper, we propose Reconstruction-to-Vector Diffusion (R2VD), which fundamentally redefines reconstruction as a manifold purification origin to establish a novel residual-guided generative dynamics paradigm. Our framework introduces a four-stage pipeline: (1) a Physical Prior Extraction (PPE) stage that mitigates early confirmation bias via dual-stream statistical guidance; (2) a Guided Manifold Purification (GMP) stage utilizing an OmniContext Autoencoder (OCA) to extract purified residual maps while preserving fragile sub-pixel topologies; (3) a Residual Score Modeling (RSM) stage where a Diffusion Transformer (DiT), guarded by a Physical Spectral Firewall (PSF), effectively isolates cross-spectral leakage; and (4) a Vector Dynamics Inference (VDI) stage that robustly decouples targets from backgrounds by evaluating high-dimensional vector interference patterns instead of conventional scalar errors. Comprehensive evaluations on eight datasets confirm that R2VD establishes a new state-of-the-art, delivering exceptional target detectability and background suppression. The code is available at https://github.com/Bondojijun/R2VD.
title Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.11390