Exploring INRs: The Cutting-Edge of Visual Computing with Architectures and Techniques Inspired by NeRF's Success.
Abstract: In this presentation, we explore INRs, recently highlighted by NeRF's success in visual computing. We will discuss architectures like ReLU-MLP, SIREN, WIRE, and DINER, and examine how these networks are conditioned using techniques such as concatenation, hypernetworks, and modulation of activation functions. Our focus is on understanding the diverse representations, architectures, and methods to generalize in this evolving field.
Who: Tomáš Kerepecký
When: 1:00 p.m. Monday, December 18
Where: The session will occur physically at the Institute of Information Theory and Automation (UTIA). Depending on the number of listeners in room 25 or 45 (café). For directions to the institute, please refer to the following link: https://www.utia.cas.cz/contacts#way
Language: Czech (if you require English, please let us know in advance)
