Das Geodätische Institut ist ein Institut der Fakultät für Bauingenieurwesen und Geodäsie.

Wir forschen und lehren im Bereich der Ingenieurgeodäsie und der geodätischen Auswertemethoden sowie im Bereich des Flächen- und Immobilienmanagements.

AKTUELLE MELDUNGEN DES GEODÄTISCHEN INSTITUTS

Paper published in PFG: Conditional Adversarial Networks for Multimodal Photo-Realistic Point Cloud Rendering

Examples for summer (middle) and winter (right) representation of the same input point cloud coloured by reflectance (left) in Hannover

Torben Peters and Claus Brenner developed a method to create photorealistic visualizations from point clouds.

We investigate whether conditional generative adversarial networks (C-GANs) are suitable for point cloud rendering. For this purpose, we created a dataset containing approximately 150,000 renderings of point cloud–image pairs. The dataset was recorded using our mobile mapping system, with capture dates that spread across 1 year. Our model learns how to predict realistically looking images from just point cloud data. We show that we can use this approach to colourize point clouds without the usage of any camera images. Additionally, we show that by parameterizing the recording date, we are even able to predict realistically looking views for different seasons, from identical input point clouds.

 

link.springer.com/article/10.1007/s41064-020-00114-z

AKTUELLE MELDUNGEN AUS DER FACHRICHTUNG GEODÄSIE UND GEOINFORMATIK

Paper published in PFG: Conditional Adversarial Networks for Multimodal Photo-Realistic Point Cloud Rendering

Examples for summer (middle) and winter (right) representation of the same input point cloud coloured by reflectance (left) in Hannover

Torben Peters and Claus Brenner developed a method to create photorealistic visualizations from point clouds.

We investigate whether conditional generative adversarial networks (C-GANs) are suitable for point cloud rendering. For this purpose, we created a dataset containing approximately 150,000 renderings of point cloud–image pairs. The dataset was recorded using our mobile mapping system, with capture dates that spread across 1 year. Our model learns how to predict realistically looking images from just point cloud data. We show that we can use this approach to colourize point clouds without the usage of any camera images. Additionally, we show that by parameterizing the recording date, we are even able to predict realistically looking views for different seasons, from identical input point clouds.

 

link.springer.com/article/10.1007/s41064-020-00114-z