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

Project A1 combines both discriminative and generative modelling to integrate the core aspects of object-based 3D world understanding into a synergistic object-centric perception system. We will develop methods to extract complete photorealistic 3D object and scene representations from a large collection of in-the-wild 2D images and videos and extend 3D generative models to be consistent with the compositional object structure of our world. We will link these object-centric reconstructions with semantic information and extend them toward open-world scenarios to handle objects beyond the training data.

• 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, until 12/2024; Professor Dr.-Ing. Andreas Geiger; Dr. Almut Sophia Koepke; Professor Dr.-Ing. Hendrik Lensch; Professor Dr. Bernhard Schölkopf, until 12/2020; Dr.-Ing. Dan Zhang