Masterthesis (f/m/x) - Neural Horizon Mapping

Salary: 49.000 - 89.000 € per year

Requirements:

Design and train a neural network for compressing and decompressing horizon maps

Use the neural network to render shadows on a planetary surface in real-time

Perform quantitative evaluations of performance and quality

Responsibilities:

We develop CosmoScout VR, an open source software for rendering realistic images of large scale planetary surfaces in real-time

We focus on applications including mission planning, generation of training data for pose estimation, and immersive analysis of georeferenced datasets

We are looking for efficient ways of encoding and storing information required for computing large scale shadows for arbitrary lighting and viewing conditions

We are exploring whether neural representations can be used to efficiently store and access occluder information of planetary terrains for computing shadows at runtime

The core of this thesis is verifying the viability of applying neural texture compression to horizon maps, auxiliary textures used in computing self-shadows of planetary terrains

Technologies:

Network

VR

Machine Learning

More:

We develop CosmoScout VR, an open source software for rendering realistic images of large scale planetary surfaces in real-time. Applications include mission planning, generation of training data for pose estimation, and immersive analysis of georeferenced datasets. One key criteria for realism is the presence of accurate shadows, however these are still challenging to produce for arbitrary scenes in real-time. We are looking for efficient ways of encoding and storing information required for computing large scale shadows for arbitrary lighting and viewing conditions.

last updated 38 week of 2026