Year: 2022
Type: conference-paper
Abstract: We present a neural extension of basic shadow mapping for fast, high quality hard and soft shadows. We compare favorably to fast pre-filtering shadow mapping, all while producing visual results on par with ray traced hard and soft shadows. We show that combining memory bandwidth-aware architecture specialization and careful temporal-window training leads to a fast, compact and easy-to-train neural shadowing method. Our technique is memory bandwidth conscious, eliminates the need for post-process temporal anti-aliasing or denoising, and supports scenes with dynamic view, emitters and geometry while remaining robust to unseen objects.
Institutions: McGill University, Nvidia (United States), Meta (United States)
Language: English
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: McGill University
OpenAlex ID: W4285981775