EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ThermalGS: Dynamic 3D Thermal Reconstruction with Gaussian Splatting

Yuxiang Liu, Xi Chen, Shen Yan, Zeyu Cui, Huaxin Xiao, Yu Liu, Maojun Zhang

Remote Sensing · 19.01.2025 · 17 (2) · 335

DOI: 10.3390/rs17020335 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 19.01.2025. Verfasst von Yuxiang Liu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Thermal infrared (TIR) images capture temperature in a non-invasive manner, making them valuable for generating 3D models that reflect the spatial distribution of thermal properties within a scene. Current TIR image-based 3D reconstruction methods primarily focus on static conditions, which only capture the spatial distribution of thermal radiation but lack the ability to represent its temporal dynamics. The absence of dedicated datasets and effective methods for dynamic 3D representation are two key challenges that hinder progress in this field. To address these challenges, we propose a novel dynamic thermal 3D reconstruction method, named ThermalGS, based on 3D Gaussian Splatting (3DGS). ThermalGS employs a data-driven approach to directly learn both scene structure and dynamic thermal representation, using RGB and TIR images as input. The position, orientation, and scale of Gaussian primitives are guided by the RGB mesh. We introduce feature encoding and embedding networks to integrate semantic and temporal information into the Gaussian primitives, allowing them to capture dynamic thermal radiation characteristics. Moreover, we construct the Thermal Scene Day-and-Night (TSDN) dataset, which includes multi-view, high-resolution aerial RGB reference images and TIR images captured at five different times throughout the day and night, providing a benchmark for dynamic thermal 3D reconstruction tasks. Experimental results demonstrate that the proposed method achieves state-of-the-art performance on the TSDN dataset, with an average absolute temperature error of 1 °C and the ability to predict surface temperature variations over time.

Förderung

  • National Science Foundation of China

Zitieren

APA

Liu, Y., Chen, X., Yan, S., Cui, Z., Xiao, H., Liu, Y., & Zhang, M. (2025). ThermalGS: Dynamic 3D Thermal Reconstruction with Gaussian Splatting. Remote Sensing, 17(2), 335. https://doi.org/10.3390/rs17020335

Vancouver

Liu Y, Chen X, Yan S, Cui Z, Xiao H, Liu Y, et al. ThermalGS: Dynamic 3D Thermal Reconstruction with Gaussian Splatting. Remote Sensing. 2025;17(2):335. doi:10.3390/rs17020335

BibTeX
@article{Liu2025,
  author = {Liu, Yuxiang and Chen, Xi and Yan, Shen and Cui, Zeyu and Xiao, Huaxin and Liu, Yu and Zhang, Maojun},
  title = {ThermalGS: Dynamic 3D Thermal Reconstruction with Gaussian Splatting},
  journal = {Remote Sensing},
  year = {2025},
  volume = {17},
  number = {2},
  pages = {335},
  doi = {10.3390/rs17020335}
}
Kostenlos starten →