Masterthesis (f/m/x) - Neural Horizon Mapping - Forschung, Ingenieur
Vor 10 Stunden
Berlin, Deutschland
Deutsches Zentrum für Luft- und Raumfahrt
Vollzeit
Kostenlos per E-Mail oder Google
Speichern Sie diesen Job und halten Sie Ihre Suche organisiert
Erstellen Sie ein kostenloses Konto, um Jobs zu speichern, Benachrichtigungen zu erstellen und von Ihrem Dashboard aus zu diesem Eintrag zurückzukehren.
Kostenlos per E-Mail oder Google
Wenn Sie fortfahren, akzeptieren Sie unsere Nutzungsbedingungen & Datenschutzerklärung.
What to expect
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.
Your tasks
Can neural representations be used to efficiently store and access occluder information of planetary terrains for computing shadows at runtime?
Lately, machine learning approaches have been used in various parts of the rendering pipeline to achieve high-quality visuals at a significantly lower memory footprint compared to non-ML pipelines. A key method is Neural texture compression: Here, a neural network is trained to reconstruct surface texture data from a compact latent representation. The core of this thesis is verifying the viability of applying this approach to so-called horizon maps, i.e. auxiliary textures used in computing self-shadows of planetary terrains.
Your profile
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
We look forward to getting to know you
If you have any questions about this position (Vacancy-ID 5118) please contact:
Jonathan Fritsch
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.
Your tasks
Can neural representations be used to efficiently store and access occluder information of planetary terrains for computing shadows at runtime?
Lately, machine learning approaches have been used in various parts of the rendering pipeline to achieve high-quality visuals at a significantly lower memory footprint compared to non-ML pipelines. A key method is Neural texture compression: Here, a neural network is trained to reconstruct surface texture data from a compact latent representation. The core of this thesis is verifying the viability of applying this approach to so-called horizon maps, i.e. auxiliary textures used in computing self-shadows of planetary terrains.
Your profile
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
We look forward to getting to know you
If you have any questions about this position (Vacancy-ID 5118) please contact:
Jonathan Fritsch