Przemysław Spurek - NeRF Based Generative Models | ML in PL 2024

Recently, generative models for 3D objects have gained much popularity in virtual (VR) and augmented reality (AR) applications. Training such models using standard 3D representations, like voxels or point clouds, is challenging and requires complex tools for proper color rendering. In order to overcome this limitation, Neural Radiance Fields (NeRFs) offer a state-of-the-art quality in synthesizing novel views of complex 3D scenes from a small subset of 2D images. In the presentation, I describe generative models which use hypernetworks paradigm to produce 3D objects represented by NeRF. The advantage of the models over existing approaches is that it produces a dedicated NeRF representation for the object without sharing some global parameters of the rendering component.

Przemysław Spurek is the leader of the Neural Rendering research team at IDEAS NCBR and a researcher in the GMUM group operating at the Jagiellonian University in Krakow. In 2014, he defended his PhD in machine learning and information theory. In 2023, he obtained his habilitation degree and became a university professor. He has published articles at prestigious international conferences such as NeurIPS, ICML, IROS, AISTATS, ECML. He co-authored the book Głębokie uczenie. Wprowadzenie [Deep Learning. Introduction] – a compendium of knowledge about the basics of AI. He was the director of PRELUDIUM, SONATA, OPUS and SONATA BIS NCN grants. Currently, his research focuses mainly on neural rendering, in particular NeRF and Gaussian Splatting models.

This talk was one of the Sponsor Talks at the ML in PL Conference 2024.

ML in PL Conference 2024 website: https://conference2024.mlinpl.org
ML in PL Association Website: https://mlinpl.org