“Inverse Global Illumination Using a Neural Radiometric Prior” by Hadadan, Lin, Novák, Rousselle and Zwicker

  • ©Saeed Hadadan, Geng Lin, Jan Novák, Fabrice Rousselle, and Matthias Zwicker

Conference:


Type:


Title:

    Inverse Global Illumination Using a Neural Radiometric Prior

Session/Category Title: Inverse Rendering: Does Anybody Know How I Got Here?


Presenter(s)/Author(s):


Moderator(s):



Abstract:


    We propose to recover scene parameters using a neural radiometric prior, which enforces a physical constraint on the optimization such that it accounts for the global illumination effects. Compared to methods based on building path integrals, we can recover scene parameters with comparable quality at considerably lower computation times.


Additional Images:

©Saeed Hadadan, Geng Lin, Jan Novák, Fabrice Rousselle, and Matthias Zwicker

Overview Page: