# A Hierarchical Architecture for Neural Materials

arXiv: https://arxiv.org/abs/2307.10135 · HTML: https://mlsanity.com/paper/2307.10135/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 19 Jul 2023.

## Builds on (most cited first, 10 of 10)

- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-time](https://mlsanity.com/paper/2202.08614/) (2022)
- [NeuTex: Neural Texture Mapping for Volumetric Neural Rendering](https://mlsanity.com/paper/2103.00762/) (2021)
- [Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation](https://mlsanity.com/paper/2205.05922/) (2022)
- [Real-Time Neural Appearance Models](https://mlsanity.com/paper/2305.02678/) (2023)
- [NeuMIP: Multi-Resolution Neural Materials](https://mlsanity.com/paper/2104.02789/) (2021)
- [NeuBTF: Neural fields for BTF encoding and transfer](https://mlsanity.com/paper/2307.01199/) (2023)
- [A Practical Ply-Based Appearance Modeling for Knitted Fabrics](https://mlsanity.com/paper/2105.02475/) (2021)
- [Mechanics-Aware Modeling of Cloth Appearance](https://mlsanity.com/paper/1904.11116/) (2019)

## Built on by (most cited first, 3 of 3)

- [ReflectanceFusion: Diffusion-based text to SVBRDF Generation](https://mlsanity.com/paper/2406.14565/) (2024)
- [VideoNeuMat: Neural Material Extraction from Generative Video Models](https://mlsanity.com/paper/2602.07272/) (2026)
- [A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering](https://mlsanity.com/paper/2608.09604/) (2026)

## Abstract (arXiv)

Neural reflectance models are capable of reproducing the spatially-varying appearance of many real-world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong shadowing effects or detailed specular highlights. In this paper, we introduce a neural appearance model that offers a new level of accuracy. Central to our model is an inception-based core network structure that captures material appearances at multiple scales using parallel-operating kernels and ensures multi-stage features through specialized convolution layers. Furthermore, we encode the inputs into frequency space, introduce a gradient-based loss, and employ it adaptive to the progress of the learning phase. We demonstrate the effectiveness of our method using a variety of synthetic and real examples.