Brent Keeth

Brent presently serves as a Distinguished Research Scientist within the NVIDIA Circuits Research Group. He focuses primarily on low energy, high bandwidth memory integration into future AI systems. 

Assessing Learned Models for Phase-only Hologram Compression

We evaluate the performance of four common learned models utilizing INR and VAE structures for compressing phase-only holograms in holographic displays. The evaluated models include a vanilla MLP, SIREN [Sitzmann et al. 2020], and FilmSIREN [Chan et al.

Jerome Gonthier

Jerome got his PhD in theoretical chemistry from EPFL (Lausanne, Switzerland) in 2013. He then moved to the US for a first post-doctoral appointment at GeorgiaTech, and then a second one at UC Berkeley starting in 2016. During this time, he worked to develop methods to better understand intermolecular interactions from first principles. In 2019, he moved to the quantum computing industry, working at Zapata Computing in the professional services organization to help industry customers understand the potential impact of quantum computers for chemistry simulations.

Jiaxiang Tang

Jiaxiang Tang is a research scientist at NVIDIA Research. He finished his Ph.D. at Peking University, advised by Prof. Gang Zeng. His research interest is in 3D Computer Vision, with a specialty in 3D reconstruction and generation.

Personal Website: https://me.kiui.moe/

Generative Detail Enhancement for Physically Based Materials

We present a tool for enhancing the detail of physically based materials using an off-the-shelf diffusion model and inverse rendering. Our goal is to enhance the visual fidelity of materials with detail that is often tedious to author, by adding signs of wear, aging, weathering, etc. As these appearance details are often rooted in real-world processes, we leverage a generative image model trained on a large dataset of natural images with corresponding visuals in context. Starting with a given geometry, UV mapping, and basic appearance, we render multiple views of the object.