Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection

TL;DR

This paper introduces R2VD, a novel hyperspectral anomaly detection framework that leverages vector diffusion and manifold purification to improve target detection and background suppression.

Contribution

It proposes a new manifold purification-based approach with a four-stage pipeline, including residual-guided generative dynamics and vector interference analysis, outperforming prior methods.

Findings

R2VD achieves state-of-the-art detection accuracy on eight datasets.

The framework effectively suppresses background noise while enhancing target detectability.

The code implementation is publicly available at the provided GitHub link.

Abstract

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.