Neural Shadow Mapping

Sayantan Datta, Derek Nowrouzezahrai, Christoph Schied, Zhao Dong

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.
BibTeX
@inproceedings{datta2022neural,
  author = {Sayantan Datta and Derek Nowrouzezahrai and Christoph Schied and Zhao Dong},
  title = {{Neural Shadow Mapping}},
  booktitle = {SIGGRAPH (Conference Paper Track)},
  year = {2022},
  doi = {10.1145/3528233.3530700},
}

Loading related content...

Figure