# 基于集合的 Transformer 用于远距离 LWIR 高光谱成像的大气补偿

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-06-06 08:00
- AIHOT 分数：43
- AIHOT 链接：https://aihot.virxact.com/items/cmq61s9bh04cusl5ixj1bb57t
- 原文链接：https://arxiv.org/abs/2606.08324

## AI 摘要

论文提出一个轻量级基于集合的深度学习框架（Set-Based Transformer），以多个不同远距离辐射测量值为输入，联合估计透射率、大气路径辐射和下行谱。使用稀疏自编码器分析学习到的表示，发现若干潜在特征在测试数据的地理一致子集上激活，尽管训练时未使用位置监督。在 MODTRAN 生成的远距离 LWIR 数据集上，所有估计产品均实现低光谱失真。代码和数据集已公开。

## 正文

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 lightweight set-based deep learning framework that takes multiple radiance measurements, collected at different standoff ranges, as input and jointly estimates transmittance, atmospheric path radiance, and a shared downwelling spectrum. We analyze the learned representation with a sparse autoencoder and 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/