Robust material inference (A01 (ehem.02))

• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: since 2017
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 276693517

The goal of this project is to develop models that recover a physical interpretation of visual scenes. In the first phase, this project fo-cused on developing robust inference methods and generative models for controlled capturing of material reflections. In the second phase we want to broaden the scope towards estimating reflection properties (BRDFs) and shape in complex scenes for unknown geometry and illumination, even allowing for a broader range of material classes. Robust and efficient material estimation in these significantly more complex settings poses several interesting challenges for which we aim to develop rather general inference strate-gies.

• DFG Programme: Collaborative Research Centres
• Subproject of: SFB 1233: Robust Vision - Inference Principles and Neural Mechanisms
• Applicant Institution: Eberhard Karls Universität Tübingen
• Project Heads: Dr. Peter Gehler; Professor Dr.-Ing. Hendrik Lensch; Professor Dr. Bernhard Schölkopf, until 12/2020