Volume XLII-2
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 519-524, 2018
https://doi.org/10.5194/isprs-archives-XLII-2-519-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 519-524, 2018
https://doi.org/10.5194/isprs-archives-XLII-2-519-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  30 May 2018

30 May 2018

THERMAL TEXTURE GENERATION AND 3D MODEL RECONSTRUCTION USING SFM AND GAN

V. V. Kniaz1,2 and V. A. Mizginov1 V. V. Kniaz and V. A. Mizginov
  • 1State Res. Institute of Aviation Systems (GosNIIAS), 125319, 7, Victorenko str., Moscow, Russia
  • 2Moscow Institute of Physics and Technology (MIPT), Russia

Keywords: infrared images, structure from motion, generative adversarial networks, object recognition, deep convolutional neural networks

Abstract. Realistic 3D models with textures representing thermal emission of the object are widely used in such fields as dynamic scene analysis, autonomous driving, and video surveillance. Structure from Motion (SfM) methods provide a robust approach for the generation of textured 3D models in the visible range. Still, automatic generation of 3D models from the infrared imagery is challenging due to an absence of the feature points and low sensor resolution. Recent advances in Generative Adversarial Networks (GAN) have proved that they can perform complex image-to-image transformations such as a transformation of day to night and generation of imagery in a different spectral range. In this paper, we propose a novel method for generation of realistic 3D models with thermal textures using the SfM pipeline and GAN. The proposed method uses visible range images as an input. The images are processed in two ways. Firstly, they are used for point matching and dense point cloud generation. Secondly, the images are fed into a GAN that performs the transformation from the visible range to the thermal range. We evaluate the proposed method using real infrared imagery captured with a FLIR ONE PRO camera. We generated a dataset with 2000 pairs of real images captured in thermal and visible range. The dataset is used to train the GAN network and to generate 3D models using SfM. The evaluation of the generated 3D models and infrared textures proved that they are similar to the ground truth model in both thermal emissivity and geometrical shape.