Set-Based Transformer for Atmospheric Compensation in Standoff LWIR Hyperspectral Imaging
Summary
A lightweight set-based deep learning framework using a transformer is presented for atmospheric compensation in passive long-wave infrared hyperspectral imaging, jointly estimating transmittance, atmospheric path radiance, and downwelling spectrum from multi-range radiance measurements.
View Cached Full Text
Cached at: 06/09/26, 08:43 AM
Paper page - Set-Based Transformer for Atmospheric Compensation in Standoff LWIR Hyperspectral Imaging
Source: https://huggingface.co/papers/2606.08324
Abstract
A lightweight deep learning framework is presented for atmospheric compensation in passive long-wave infrared hyperspectral imaging, enabling joint estimation of transmittance, atmospheric path radiance, and downwelling spectrum from multi-range radiance measurements.
Passive long-wave infrared (LWIR) hyperspectral imaging under a standoff geometry depends on atmospheric absorption and emission, as well as reflected radiance, thus making atmospheric compensation essential to get knowledge of a target of interest. Despite its importance, this compensation has been largely overlooked due to its practical and modeling difficulty. In this paper, we present a lightweightset-based deep learning frameworkthat takes multiple radiance measurements, collected at different standoff ranges, as input and jointly estimates transmittance,atmospheric path radiance, and a shareddownwelling spectrum. We analyze the learned representation with asparse autoencoderand observe that several latent features do activate on geographically coherent subsets of the test data despite the absence of location supervision. Experiments on a MODTRAN generated standoff LWIR dataset demonstrate low spectral distortion across all estimated products. The dataset and code is publicly available at: https://factral.co/SAE-LWIR/
View arXiv pageView PDFProject pageGitHub0Add to collection
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.08324 in a model README.md to link it from this page.
Datasets citing this paper1
#### SemilleroCV/SAE-LWIR Updatedabout 6 hours ago • 41 • 1
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.08324 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstruction
Lite3R is a model-agnostic framework that improves the efficiency of transformer-based 3D reconstruction using sparse linear attention and FP8-aware quantization. It reduces latency and memory usage by up to 2.4x while maintaining geometric accuracy on backbones like VGGT and DA3-Large.
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
UniverSat introduces a Universal Patch Encoder for Vision Transformers that enables robust, sensor-agnostic spatial feature extraction across diverse Earth Observation data types, achieving strong results on classification and segmentation benchmarks.
BA-T: An Iterative Transformer for Two-View Bundle Adjustment
BA-T is an iterative Transformer architecture for two-view bundle adjustment that improves 3D reconstruction accuracy and cross-view consistency using a lightweight design with only 16% of conventional decoder parameters, matching or surpassing larger models.
RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
RF-DETR introduces a lightweight detection transformer that uses weight-sharing neural architecture search to achieve state-of-the-art real-time object detection, outperforming prior methods on COCO and Roboflow100-VL while running up to 20x faster.
Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins
This paper evaluates encoder-only Transformer and LSTM models for streamflow prediction in ungauged basins using NOAA's National Water Model simulations. Results show LSTM outperforms Transformer, and incorporating downstream information significantly improves prediction skill across both architectures.