Back to Search
Start Over
Neural Shadow Mapping
- Source :
- ACM SIGGRAPH 2022 Conference Proceedings
- Publication Year :
- 2023
-
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.<br />Comment: Project Page: https://sayan1an.github.io/neuralShadowMapping.html
- Subjects :
- Computer Science - Graphics
Subjects
Details
- Database :
- arXiv
- Journal :
- ACM SIGGRAPH 2022 Conference Proceedings
- Publication Type :
- Report
- Accession number :
- edsarx.2301.05262
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1145/3528233.3530700