GAIL Seminar Series: Why do we not have foundation models in Computer Vision? In his GAIL Seminar, Dr Christian Rupprecht, Associate Professor of Computer Science, University of Oxford, explore and later discuss why it is hard to represent all of computer vision in a “foundation model”. During the course of his talk, Dr Rupprecht will discuss various 2D and 3D models that have undoubtedly made progress towards this goal and how we could use them in the foundation model sense for other tasks. This will culminate in discussion of a potential alternative to foundation models, data generation, with some initial ideas how those could help change the typical training paradigm (data collection, labelling, and training) that we have been following for over a decade now. Biography After completing his BSc and MSc at the Technical University of Munich, Christian Rupprecht obtained his PhD in 2018 advised by Nassir Navab (Technical University of Munich) and Gregory D Hager (Johns Hopkins University). He joined Oxford University first as a PostDoc in Engineering Science with Andrea Vedaldi, then as a Departmental Lecturer in Computer Vision, and now an Associate Professor in Computer Science and Tutorial Fellow at Magdalen College.Christian Rupprecht is interested in unsupervised scene understanding in {2,3,4}D from images and videos. His research is focused on discovering and reconstructing objects and their interactions without the help of manual annotations. Jun 06 2025 11.00 - 12.30 GAIL Seminar Series: Why do we not have foundation models in Computer Vision? In his GAIL Seminar, Dr Christian Rupprecht, University of Oxford, will explore the difficulty of representing all of Computer Vision in a “foundation model”. G.03 Informatics Forum Location Register
GAIL Seminar Series: Why do we not have foundation models in Computer Vision? In his GAIL Seminar, Dr Christian Rupprecht, Associate Professor of Computer Science, University of Oxford, explore and later discuss why it is hard to represent all of computer vision in a “foundation model”. During the course of his talk, Dr Rupprecht will discuss various 2D and 3D models that have undoubtedly made progress towards this goal and how we could use them in the foundation model sense for other tasks. This will culminate in discussion of a potential alternative to foundation models, data generation, with some initial ideas how those could help change the typical training paradigm (data collection, labelling, and training) that we have been following for over a decade now. Biography After completing his BSc and MSc at the Technical University of Munich, Christian Rupprecht obtained his PhD in 2018 advised by Nassir Navab (Technical University of Munich) and Gregory D Hager (Johns Hopkins University). He joined Oxford University first as a PostDoc in Engineering Science with Andrea Vedaldi, then as a Departmental Lecturer in Computer Vision, and now an Associate Professor in Computer Science and Tutorial Fellow at Magdalen College.Christian Rupprecht is interested in unsupervised scene understanding in {2,3,4}D from images and videos. His research is focused on discovering and reconstructing objects and their interactions without the help of manual annotations. Jun 06 2025 11.00 - 12.30 GAIL Seminar Series: Why do we not have foundation models in Computer Vision? In his GAIL Seminar, Dr Christian Rupprecht, University of Oxford, will explore the difficulty of representing all of Computer Vision in a “foundation model”. G.03 Informatics Forum Location Register
Jun 06 2025 11.00 - 12.30 GAIL Seminar Series: Why do we not have foundation models in Computer Vision? In his GAIL Seminar, Dr Christian Rupprecht, University of Oxford, will explore the difficulty of representing all of Computer Vision in a “foundation model”.
