arXiv:2609.28283v1 Announce Type: new Abstract: Several foundation models dedicated to hyperspectral images have recently been made available. These models are trained on large unlabeled datasets and...
arXiv:2602.18741v3 Announce Type: replace-cross Abstract: Spectral rendering reproduces the wavelength-dependent appearance that RGB rendering cannot: metamerism, colour shifts under spectrally rich...
arXiv:2609.24819v1 Announce Type: cross Abstract: Mesopic and low-light display transforms require, as their driving signal, a per-pixel scotopic-to-photopic luminance ratio (S/P); the exact spectral...
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...
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.
The paper critiques the common practice of random pixel splits in hyperspectral image classification, noting that such splits allow test pixels to be adjacent to training pixels, inflating accuracy. It proposes a leakage‑free evaluation protocol that enforces spatial separation based on the model’s receptive field and applies it to ten diverse architectures, finding a significant drop in Macro‑F1 (average 0.147) and substantial changes in model rankings. The study also shows that all ten models misclassify the same pixels, indicating a spectral ambiguity in the data that current methods cannot resolve.
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.
arXiv:2610.23733v1 Announce Type: new Abstract: Partial occlusion makes object detection difficult when visible regions have weak texture or similar appearance. Hyperspectral imaging provides materia...
arXiv:2606.26738v3 Announce Type: replace Abstract: While recent advancements in generative image editing models have achieved stunning visual fidelity, it remains an open question whether these syst...
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...
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arnold networks, and se...
SUPRA-Tex is a new method for single‑image 3D generation that dresses a 3D mesh with relightable materials while preserving the visual details of a reference image. It decouples visible‑material estimation, surface alignment, and observation‑guided 3D completion, allowing a 3D generator trained on limited data to focus on preserving visible evidence and completing unobserved surfaces. The approach uses an MLLM‑based image editor to predict lighting‑separated PBR maps, projects them onto the visible surface, encodes them with a pretrained material VAE, and employs an interleaved flow transformer to generate complete material latents, achieving state‑of‑the‑art performance on geometry‑conditioned texturing and end‑to‑end asset generation.