arXiv Computer Vision
Spectral World Renderer: Unified 3D Hyperspectral Unmixing
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 24
Benchmarking Hyperspectral Foundation Models for Hyperspectral Unmixing
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 Computer Vision
Sep 22
Spectral Rendering Without a Spectral Renderer: Learned Spectral Codes for RGB Pipelines
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 Computer Vision
Sep 22
When is a closed-form RGB->S/P ratio adequate? A hyperspectral characterization on natural scenes for mesopic display
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...
Hugging Face Trending Papers
Sep 29
HyperSAM: A Promptable Foundation Model for Hyperspectral Remote Sensing
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...
arXiv Computer Vision
Aug 31
HyperVision: A Channel-Adaptive Ground-Based Hyperspectral Vision Pre-trained Backbone
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.
arXiv Machine Learning
Sep 3
Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint Evaluation
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.