Rapid mineral characterization is essential for applications ranging from mineral exploration to industrial ore processing. To this end, Hyperspectral Imaging (HSI) has emerged as a promising sensing...
arXiv:2608.30537v1 Announce Type: cross Abstract: Rapid mineral characterization is essential for applications ranging from mineral exploration to industrial ore processing. To this end, Hyperspectra...
AGSA-Net is a hyperspectral image classification framework that incorporates spectral unmixing priors through an abundance-guided self‑attention network. It first estimates physically meaningful subpixel abundance maps with non‑negativity and sum‑to‑one constraints, then uses these abundances to build an affinity prior that directs a spectral transformer to focus on class‑discriminative interactions. The transformer features are fused with compact abundance descriptors for final classification, and experiments on Indian Pines, Augsburg, and Berlin datasets show improved performance, especially in heterogeneous urban scenes.
Hyperspectral remote sensing provides dense spectral measurements that are indispensable for material-level Earth observation, yet the construction of a general-purpose hyperspectral foundation model...
HyperSAM is a promptable foundation model for hyperspectral remote sensing that integrates a data‑centric synthesis pipeline with a spectral adaptation architecture based on Segment Anything Model 3 (SAM3). The model generates full‑spectrum hyperspectral cubes from high‑resolution multispectral imagery using a physics‑informed abundance‑transfer generator, and employs SAM3‑derived pseudo‑masks for object‑centric supervision. With a frozen SAM3 RGB branch, a trainable hyperspectral encoder, ControlNet‑style feature injection, and a mixture‑of‑experts mask refiner, HyperSAM demonstrates strong generalization across diverse hyperspectral tasks such as classification, anomaly detection, change detection, target detection, and airborne oil‑spill mapping.
The paper presents a physics‑aware, multi‑domain self‑supervised learning framework for Raman spectroscopy that uses a masked autoencoder with a sparse Voigt‑profile decoder and a denoising objective. It learns transferable spectral representations from diverse biological, chemical, forensic, and materials datasets, and demonstrates improved performance on substance classification, component identification, concentration estimation, and spectral denoising. The study shows that self‑supervised pretraining is especially beneficial for tasks with limited labeled data, that attention‑based probing reveals richer information than linear probing, and that larger encoders benefit more from pretraining.
The paper presents the first publicly available hyperspectral imaging (HSI) dataset of shredded black plastics from end‑of‑life vehicle waste, covering four industrial polymers across RGB, VNIR, SWIR, and MWIR modalities. It introduces a multi‑modal spectral‑spatial framework that combines foreground isolation, pixel‑wise classification, and object‑level majority voting, leveraging hyperspectral transformers and chemometric band selection to accurately classify complex black plastics. The study benchmarks nine processing methods—including chemometric, machine learning, and deep learning architectures—providing a reproducible, comprehensive benchmark for industrial hyperspectral object analysis.
arXiv:2603. 06673v2 Announce Type: replace-cross Abstract: Spectroscopic imaging (SI) has become central to heritage science because it enables non-invasive, spatially resolved characterisation of materials in artefacts.
The paper introduces a biologically informed, semi‑supervised deep learning approach for hyperspectral tree species classification that fuses hyperspectral imaging and airborne laser scanning data with ecological knowledge. It uses a canopy graph and biologically inspired pseudo‑labelling, enhanced by expert priors derived from a large language model‑assisted, citation‑constrained workflow, to improve classification accuracy. Experiments on two real‑world forest datasets demonstrate macro‑F1 gains of 6.01 and 4.85 percentage points over leading classical HSI–ALS pipelines.
The paper introduces a self‑supervised, physics‑aware deep learning method for hyperspectral image restoration and super‑resolution in biomedical imaging. It achieves 16× pixel super‑resolution and 12× faster imaging without external training data, preserving biological integrity across synthetic and experimental samples. The approach also reveals disease‑associated metabolic changes and offers physical insights into the model’s workings, with all code released as open source.
arXiv:2604.08884v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on RGB image understanding, yet their ability to use spectral evide...
HyperVision introduces the first ground‑based hyperspectral pre‑trained backbone, addressing challenges of varying spectral configurations, limited annotations, and dataset diversity. It employs a channel‑adaptive dynamic embedding to unify heterogeneous inputs, a multi‑source pseudo‑labeling strategy combining SAM2 spatial cues with HyperFree spectral details, and cross‑modal knowledge distillation from a pre‑trained RGB vision model. Trained on 15k images from 26 datasets, HyperVision achieves significant improvements—up to 16.3% relative gain in hyperspectral semantic segmentation, 2.1% in object tracking AUC, and 35.5% reduction in salient object detection MAE—while requiring only head‑only adaptation.