Material-Segmented Per-Pixel Emissivity Correction for Thermographic Anomaly Detection in Cultural Heritage Digital Twins
Quick Answer
This study introduces a training-free pipeline for per-pixel emissivity correction in thermography of cultural heritage, achieving a mean absolute error reduction from 1.97 K to 0.91 K on a synthetic benchmark.
Quick Take
The method utilizes SAM 3.1 segmentation and a material-keyed LWIR emissivity table, revealing that weathered heritage surfaces often cluster near conventional emissivity defaults, limiting correction effectiveness.
Key Points
- Achieves a mean absolute error reduction from 1.97 K to 0.91 K on synthetic benchmarks.
- Utilizes SAM 3.1 segmentation for accurate per-pixel emissivity mapping.
- Finds that weathered outdoor heritage emissivities cluster near conventional defaults.
- Demonstrates limited correction effectiveness on typical surfaces with low-emissivity exceptions.
- Identifies failure modes where segmentation matches appearance rather than material.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Quantitative longwave thermography of heritage surfaces is limited by the global-constant emissivity assumption in inverse-Planck temperature retrieval; on heterogeneous surfaces emissivity varies within one field of view, producing apparent-temperature artifacts that mimic and mask subsurface anomalies. We present a training-free pipeline that derives per-pixel emissivity by applying SAM 3.1 open-vocabulary segmentation to a colocated, co-calibrated RGB channel, mapping segments to a material-keyed LWIR emissivity table compiled from primary measurement literature, and propagating the field into a per-pixel inverse-Planck solve on raw radiometric data. Lacking any public dataset with raw radiometry, a temperature reference, and a colocated RGB camera, we evaluate on a physics-based synthetic benchmark and four real datasets. On the benchmark, under a palette spanning the low-emissivity exceptions, the correction cuts mean absolute error from 1.97 K to 0.91 K at 20 K contrast and, with an accurate table, beats the best fitted global constant on every layout; on a heritage-realistic emissivity distribution it does not. We contribute a quantified operating-regime map, and a measurement-backed finding that tempers the heritage claim: weathered outdoor heritage emissivities cluster near the conventional default, so the correction is small on typical surfaces and concentrated on genuine low-emissivity exceptions. We characterize the dominant failure mode, in which open-vocabulary segmentation matches appearance rather than material, and the contraindicated regime in which emissivity-defined anomalies are suppressed.
| Comments: | 13 pages 5 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2608.02964 [cs.CV] |
| (or arXiv:2608.02964v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2608.02964 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Scott McAvoy [view email]
[v1]
Mon, 3 Aug 2026 23:58:44 UTC (904 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.