GTSM: Gaussian Splatting with Thermal State-Space Dynamics for Spatio-Temporal Thermal Field Reconstruction and Prediction

Computer Science > Computer Vision and Pattern Recognition arXiv:2610.26918 (cs) [Submitted on 17 Oct 2026] Title: GTSM: Gaussian Splatting with Thermal State-Space Dynamics for Spatio-Temporal Thermal Field Reconstruction and Prediction Authors: Yunpeng Zhao, Haoxiang Zhang, Chao Liu.

计算机科学 > 计算机视觉与模式识别 arXiv:2610.26918 (cs) [提交于 2026 年 10 月 17 日] 标题：GTSM：用于时空热场重建与预测的具有热状态空间动力学的高斯溅射，作者：Yunpeng Zhao, Haoxiang Zhang, Chao Liu。

Abstract: Temperature-field reconstruction and prediction are important for condition monitoring, process analysis, and state assessment in industrial and dynamic environments. This work aims to recover a four-dimensional spatio-temporal thermal state field directly from two-dimensional observations, without requiring a predefined 3D model, prescribed thermodynamic equation, or predefined heating/cooling trajectory.

摘要：温度场重建与预测对于工业和动态环境中的状态监测、过程分析及状态评估至关重要。本工作旨在直接从二维观测中恢复四维时空热状态场，且无需预定义的 3D 模型、规定的热力学方程或预设的加热/冷却轨迹。

To this end, we propose the Gaussian Thermal State-Space Model (GTSM), which represents thermal evolution through a shared scene-level latent process and Gaussian-specific local thermal states. The resulting continuous dynamics are propagated using differentiable RK2 integration, allowing thermal evolution to be inferred from multi-view and multi-temporal observations and continuously extrapolated beyond the observed interval.

为此，我们提出了高斯热状态空间模型（GTSM），它通过共享的场景级潜在过程和高斯特定的局部热状态来表示热演化。由此产生的连续动力学使用可微 RK2 积分进行传播，从而允许从多视角和多时间观测中推断热演化，并可在观测区间之外进行连续外推。

GTSM is designed as a backbone-agnostic thermal dynamics module for Gaussian representations and can be integrated with both static 3D Gaussian Splatting and dynamic 4D Gaussian Splatting, supporting thermal reconstruction and prediction under both static and time-varying target geometry. The reconstructed representation further enables novel-view thermal rendering and future-time thermal-state prediction.

GTSM 被设计为一种用于高斯表示的、与骨干网络无关的热动力学模块，可以与静态 3D 高斯溅射和动态 4D 高斯溅射集成，支持在静态和时变目标几何结构下的热重建与预测。重建后的表示进一步实现了新视角热渲染和未来时间热状态预测。

Experiments on real infrared sequences and synthetic dynamic thermal data demonstrate improved reconstruction accuracy and substantially stronger temporal extrapolation than representative baselines, while also validating the applicability of GTSM to deforming targets.

在真实红外序列和合成动态热数据上的实验表明，与代表性基线相比，该方法提高了重建精度并具有更强的时序外推能力，同时也验证了 GTSM 在变形目标上的适用性。