# Neural Shadow Mapping

arXiv: https://arxiv.org/abs/2301.05262 · HTML: https://mlsanity.com/paper/2301.05262/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2023.

## Built on by (most cited first, 4 of 4)

- [Real-Time Neural Materials using Block-Compressed Features](https://mlsanity.com/paper/2311.16121/) (2023)
- [Deep and Fast Approximate Order Independent Transparency](https://mlsanity.com/paper/2305.10197/) (2023)
- [Efficient Graphics Representation with Differentiable Indirection](https://mlsanity.com/paper/2309.08387/) (2023)
- [STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Rendering](https://mlsanity.com/paper/2606.16747/) (2026)

## Abstract (arXiv)

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.