Ivan Skorokhodov on Generative Models for Neural Fields | Toronto AIR Seminar

Abstract: Deep generative models are deep learning-based methods that are optimized to synthesize samples of a given distribution. During the past years, they have attracted a lot of interest from the research community, and the developed tools now enjoy many practical applications in content creation and editing. In computer vision, such 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 talk, we'll discuss generative modeling methods for images, videos, and 3D objects which treat the underlying data in such a form. This perspective can yield state-of-the-art synthesis quality and many useful practical benefits, like interpolation/extrapolation capabilities, geometric inductive biases, and more efficient training and inference. Paper: Skorokhodov, Ivan, et al. "Aligning latent and image spaces to connect the unconnectable." ICCV. 2021. Skorokhodov, Ivan, et al. "StyleGAN-V." CVPR. 2022. Skorokhodov, Ivan, et al. "3D generation on ImageNet." ICLR. 2023. Bio: Ivan received his PhD degree from KAUST in March 2023, where he was a part of Visual Computing Center, supervised by prof. Peter Wonka and prof. Mohamed Elhoseiny. He does deep learning and his research interests include generative models and neural rendering. Before that, he was a deep learning researcher at MIPT for 2 years — first, working on NLP and then, on loss landscape analysis. Before MIPT, He was a software engineer at Yandex for 1.5 years. Toronto AIR Seminar: The Toronto AI Robotics Seminar Series is a set of events featuring young robotics and AI experts. The talks are given by local as well as global speakers and organized by the Faculty and Students at University of Toronto’s Department of Computer Science. We welcome students, researchers and robotics enthusiasts from around the world to join us and interact with the Toronto Robotics Community. Find out more at: https://robotics.cs.toronto.edu/toron...