ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance Fields
This work addresses thermal reconstruction for applications like building energy analysis, but it is incremental as it builds on existing NeRF methods with a multimodal extension.
The paper tackles the problem of inconsistent geometry and temperature data in thermal scene reconstruction by proposing ThermoNeRF, a multimodal Neural Radiance Fields approach that jointly renders RGB and thermal views, achieving an average mean absolute error of 1.13°C for buildings and 0.41°C for other scenes, which is over 50% better than baseline methods.
Thermal scene reconstruction holds great potential for various applications, such as analyzing building energy consumption and performing non-destructive infrastructure testing. However, existing methods typically require dense scene measurements and often rely on RGB images for 3D geometry reconstruction, projecting thermal information post-reconstruction. This can lead to inconsistencies between the reconstructed geometry and temperature data and their actual values. To address this challenge, we propose ThermoNeRF, a novel multimodal approach based on Neural Radiance Fields that jointly renders new RGB and thermal views of a scene, and ThermoScenes, a dataset of paired RGB+thermal images comprising 8 scenes of building facades and 8 scenes of everyday objects. To address the lack of texture in thermal images, ThermoNeRF uses paired RGB and thermal images to learn scene density, while separate networks estimate color and temperature data. Unlike comparable studies, our focus is on temperature reconstruction and experimental results demonstrate that ThermoNeRF achieves an average mean absolute error of 1.13C and 0.41C for temperature estimation in buildings and other scenes, respectively, representing an improvement of over 50% compared to using concatenated RGB+thermal data as input to a standard NeRF. Code and dataset are available online.