Next-generation multi-sensor systems
The Geodetic Institute (GIH) at Leibniz Universität Hannover teaches and conducts research in the fields of Engineering Geodesy and Geodetic Evaluation Methods as well as Land and Property Management.
The primary field of reseach and activities in the area of Engineering Geodesy and Geodetic Evaluation Methods include the quality assessment of data and measurement systems, terrestrial laser scanning, geodetic monitoring of objects, efficiency optimisation and control of measurement processes as well as the application of evaluation methods (filtering, parameter estimation).
Land and Property Management offers implementation-orientated strategies and cooperative solutions for the sustainable development of villages and towns as well as developed an undeveloped land both indoors and outdoors. It also insures the expert valuation of properties and - by analysing their spatal and temporal development - the transparency of property markets.
Latest news from the Geodetic Institute
Paper published in PFG: Conditional Adversarial Networks for Multimodal Photo-Realistic Point Cloud Rendering
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.
Current news from the Department of Geodesy and Geoinformatics
Paper published in PFG: Conditional Adversarial Networks for Multimodal Photo-Realistic Point Cloud Rendering
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.
