PhD Student,
Computer Science
Wednesday, February 15, 2023, 20:10
- 22:00
B1, L2, R2202
Contact Person
In computer vision, generative AI models are typically built for images, videos, and 3D objects. Recently, there has emerged a paradigm of neural fields, which unifies the representations of such types of data by parametrizing them via neural networks. In this thesis, we develop generative models for images, videos, and 3D scenes which treat the underlying data in such a form and explore the benefits which such a perspective provides.