NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics

2025-03-05

AI Summary

Existing thermal infrared reconstruction methods are limited to static scenes, neglect environmental influences on thermal radiation, and fail to model the time-varying nature of temperature—particularly at night. This work proposes the first dynamic 4D thermal radiation reconstruction framework tailored for nighttime scenarios. Our method uniquely integrates thermodynamic principles—including convective heat transfer and radiative cooling—with 4D Gaussian splatting to construct a physically interpretable, time-varying temperature field. We design a thermodynamics-driven neural network that jointly predicts emissivity, convective heat transfer coefficient, and specific heat capacity. Furthermore, we introduce the first nighttime dynamic thermal imaging dataset and a physics-guided temporal temperature optimization strategy. Experiments demonstrate that our approach achieves surface temperature prediction accuracy within ±1°C under nighttime conditions, significantly outperforming state-of-the-art static thermal reconstruction methods.

Technology Category

• Computer Vision: Low Level & Physics-based Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Thermal infrared imaging offers the advantage of all-weather capability, enabling non-intrusive measurement of an object's surface temperature. Consequently, thermal infrared images are employed to reconstruct 3D models that accurately reflect the temperature distribution of a scene, aiding in applications such as building monitoring and energy management. However, existing approaches predominantly focus on static 3D reconstruction for a single time period, overlooking the impact of environmental factors on thermal radiation and failing to predict or analyze temperature variations over time. To address these challenges, we propose the NTR-Gaussian method, which treats temperature as a form of thermal radiation, incorporating elements like convective heat transfer and radiative heat dissipation. Our approach utilizes neural networks to predict thermodynamic parameters such as emissivity, convective heat transfer coefficient, and heat capacity. By integrating these predictions, we can accurately forecast thermal temperatures at various times throughout a nighttime scene. Furthermore, we introduce a dynamic dataset specifically for nighttime thermal imagery. Extensive experiments and evaluations demonstrate that NTR-Gaussian significantly outperforms comparison methods in thermal reconstruction, achieving a predicted temperature error within 1 degree Celsius.

Problem

• Dynamic thermal reconstruction for nighttime scenes
• Incorporating thermodynamics to predict temperature variations
• Improving accuracy in thermal imaging for building monitoring

Innovation

• Uses 4D Gaussian splatting for thermal reconstruction
• Incorporates neural networks for thermodynamic parameter prediction
• Introduces dynamic dataset for nighttime thermal imagery