HSI-VAR: Rethinking Hyperspectral Restoration through Spatial-Spectral Visual Autoregression
Xiangming Wang, Benteng Sun, Yungeng Liu, Haijin Zeng, Yongyong Chen, Jingyong Su, Jie Liu

TL;DR
HSI-VAR introduces a novel autoregressive approach for hyperspectral image restoration that models spatial-spectral dependencies, significantly reducing computational costs while achieving state-of-the-art results.
Contribution
The paper proposes HSI-VAR, a new autoregressive model for HSI restoration that incorporates latent-condition alignment, degradation-aware guidance, and a spatial-spectral adaptation module.
Findings
Achieves 3.77 dB PSNR improvement on ICVL benchmark.
Reduces inference time by up to 95.5 times compared to diffusion models.
Outperforms existing methods in structure preservation and efficiency.
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)…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRemote-Sensing Image Classification · Image and Signal Denoising Methods · Advanced Image Fusion Techniques
