github: <a href=\"https://github.com/Factral/SAE-LWIR\" rel=\"nofollow\">https://github.com/Factral/SAE-LWIR</a></p>\n","updatedAt":"2026-06-09T02:23:48.864Z","author":{"_id":"62eee05235b4995510af75bf","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1659822155165-noauth.jpeg","fullname":"Fabian Perez","name":"Factral","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.9158309102058411},"editors":["Factral"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1659822155165-noauth.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.08324","authors":[{"_id":"6a2778bc6dde1c5ef75bcefa","name":"Fabian Perez","hidden":false},{"_id":"6a2778bc6dde1c5ef75bcefb","name":"Nicolas Quintero","hidden":false},{"_id":"6a2778bc6dde1c5ef75bcefc","name":"Jeferson Acevedo","hidden":false},{"_id":"6a2778bc6dde1c5ef75bcefd","name":"Hoover Rueda-Chacon","hidden":false}],"mediaUrls":["https://cdn-uploads.huggingface.co/production/uploads/62eee05235b4995510af75bf/yXFxmdTQPh_4dVkjVCsD8.png"],"publishedAt":"2026-06-06T00:00:00.000Z","submittedOnDailyAt":"2026-06-09T00:00:00.000Z","title":"Set-Based Transformer for Atmospheric Compensation in Standoff LWIR Hyperspectral Imaging","submittedOnDailyBy":{"_id":"62eee05235b4995510af75bf","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1659822155165-noauth.jpeg","isPro":false,"fullname":"Fabian Perez","user":"Factral","type":"user","name":"Factral"},"summary":"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/","upvotes":0,"discussionId":"6a2778bc6dde1c5ef75bcefe","projectPage":"https://factral.co/SAE-LWIR/","githubRepo":"https://github.com/Factral/SAE-LWIR","githubRepoAddedBy":"user","ai_summary":"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.","ai_keywords":["set-based deep learning framework","sparse autoencoder","transmittance estimation","atmospheric path radiance","downwelling spectrum","standoff LWIR imaging","MODTRAN dataset"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"]}">

Cite arxiv.org/abs/2606.08324 in a model README.md to link it from this page.

Cite arxiv.org/abs/2606.08324 in a Space README.md to link it from this page.

Add this paper to a collection to link it from this page.