Timezone: »

 
Poster
Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition
Mark Boss · Varun Jampani · Raphael Braun · Ce Liu · Jonathan Barron · Hendrik PA Lensch

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @ Virtual
in Poster Session 6 »

Decomposing a scene into its shape, reflectance and illumination is a fundamental problem in computer vision and graphics. Neural approaches such as NeRF have achieved remarkable success in view synthesis, but do not explicitly perform decomposition and instead operate exclusively on radiance (the product of reflectance and illumination). Extensions to NeRF, such as NeRD, can perform decomposition but struggle to accurately recover detailed illumination, thereby significantly limiting realism. We propose a novel reflectance decomposition network that can estimate shape, BRDF, and per-image illumination given a set of object images captured under varying illumination. Our key technique is a novel illumination integration network called Neural-PIL that replaces a costly illumination integral operation in the rendering with a simple network query. In addition, we also learn deep low-dimensional priors on BRDF and illumination representations using novel smooth manifold auto-encoders. Our decompositions can result in considerably better BRDF and light estimates enabling more accurate novel view-synthesis and relighting compared to prior art. Project page: https://markboss.me/publication/2021-neural-pil/

Keywords: Vision · Graph Learning

Author Information

Mark Boss (University of Tübingen)
Varun Jampani (Google)
Raphael Braun (University of Tuebingen)
Ce Liu (Microsoft)
Jonathan Barron (Google Research)
Hendrik PA Lensch (University of Tübingen)

More from the Same Authors