HSI-VAR: Rethinking Hyperspectral Restoration through Spatial-Spectral Visual Autoregression

2026-01-31

AI Summary

This study addresses the challenge of hyperspectral image restoration under complex real-world degradations—including noise, blur, and missing spectral bands—where existing methods often suffer from high computational cost or excessive smoothing of structural details. To overcome these limitations, the work formulates restoration as an autoregressive generation task in a latent space and introduces three key innovations: latent-space conditional alignment, degradation-aware guidance, and a spatial-spectral adaptive module. These components collectively enable an efficient vision autoregressive architecture that jointly models spatial and spectral information. The proposed method achieves state-of-the-art performance across nine benchmarks, yielding a 3.77 dB PSNR improvement on the ICVL dataset and accelerating inference by 95.5× compared to diffusion-based models.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Hyperspectral images (HSIs) capture richer spatial-spectral information beyond RGB, yet real-world HSIs often suffer from a composite mix of degradations, such as noise, blur, and missing bands. Existing generative approaches for HSI restoration like diffusion models require hundreds of iterative steps, making them computationally impractical for high-dimensional HSIs. While regression models tend to produce oversmoothed results, failing to preserve critical structural details. We break this impasse by introducing HSI-VAR, rethinking HSI restoration as an autoregressive generation problem, where spectral and spatial dependencies can be progressively modeled rather than globally reconstructed. HSI-VAR incorporates three key innovations: (1) Latent-condition alignment, which couples semantic consistency between latent priors and conditional embeddings for precise reconstruction; (2) Degradation-aware guidance, which uniquely encodes mixed degradations as linear combinations in the embedding space for automatic control, remarkably achieving a nearly $50\%$ reduction in computational cost at inference; (3) A spatial-spectral adaptation module that refines details across both domains in the decoding phase. Extensive experiments on nine all-in-one HSI restoration benchmarks confirm HSI-VAR's state-of-the-art performance, achieving a 3.77 dB PSNR improvement on \textbf{\textit{ICVL}} and offering superior structure preservation with an inference speed-up of up to $95.5 \times$ compared with diffusion-based methods, making it a highly practical solution for real-world HSI restoration.

Problem

• hyperspectral image restoration
• composite degradation
• computational efficiency
• structural detail preservation

Innovation

• hyperspectral restoration
• visual autoregression
• degradation-aware guidance
• spatial-spectral adaptation
• latent-condition alignment