We look forward to seeing you online on Thursday, August 31.
Abstract: Recent years have seen strong advances in learning general priors for 3D scene understanding tasks, while the burgeoning rise of interest in neural scene representations has reinvigorated per-scene optimization paradigms. In this talk, we start by leveraging 3D scene optimization to generate view-consistent panoptic understanding in neural fields. We then explore learning a 3D texture manifold as a prior for test-time optimization to support texturing from arbitrary RGB image queries, where the learned prior serves as regularization across incongruous geometry and pose. Next, we introduce a new paradigm to learn a shape manifold from optimized neural fields that enables a dimension-agnostic approach for high-dimensional generative modeling. Finally, we present a new dataset of high-fidelity 3D scenes to open new outlooks on 3D generative modeling.
Bio: Angela Dai is an Assistant Professor at the Technical University of Munich where she leads the 3D AI group. Angela's research focuses on understanding how the 3D world around us can be modeled and semantically understood. Previously, she received her PhD in computer science from Stanford in 2018 and her BSE in computer science from Princeton in 2013. Her research has been recognized through an ERC Starting Grant, Eurographics Young Researcher Award, Google Research Scholar Award, ZDB Junior Research Group Award, and ACM SIGGRAPH Outstanding Doctoral Dissertation Honorable Mention.
