Multimodal Neural Radiance Fields for Thermal Novel View Synthesis

EPFL Pavillon Cup

Authors: Mariam Hassan, Florent Forest, Olga Fink, Malcolm Mielle

PDF  Code  Dataset URL

Method

We propose a novel multimodal approach based on Neural Radiance Fields, capable of rendering new RGB and thermal views of a scene jointly.

Summary

Thermal images are textureless and suffer from the ghosting effect. To overcome the lack of texture in thermal images, we use paired RGB and thermal images to learn scene density, while distinct networks estimate color and temperature information.

Architecture of the network

Furthermore, we introduce ThermoScenes, a new dataset to palliate the lack of available RGB+thermal datasets for scene reconstruction.

Results

Experimental results validate that ThermoNeRF achieves accurate thermal image synthesis, with an average mean absolute error of 1.5C, an improvement of over 50% compared to using concatenated RGB+thermal data with Nerfacto, a state-of-the-art NeRF method.