# Random-Access Neural Compression of Material Textures

arXiv: https://arxiv.org/abs/2305.17105 · HTML: https://mlsanity.com/paper/2305.17105/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 97 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [BACON: Band-limited Coordinate Networks for Multiscale Scene Representation](https://mlsanity.com/paper/2112.04645/) (2021)
- [Nonlinear Transform Coding](https://mlsanity.com/paper/2007.03034/) (2020)
- [Real-Time Adaptive Image Compression](https://mlsanity.com/paper/1705.05823/) (2017)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation](https://mlsanity.com/paper/2204.05735/) (2022)

## Built on by (most cited first, 23 of 23)

- [Image-GS: Content-Adaptive Image Representation via 2D Gaussians](https://mlsanity.com/paper/2407.01866/) (2024)
- [Compact Neural Graphics Primitives with Learned Hash Probing](https://mlsanity.com/paper/2312.17241/) (2023)
- [Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting](https://mlsanity.com/paper/2506.23479/) (2025)
- [Filtering After Shading With Stochastic Texture Filtering](https://mlsanity.com/paper/2407.06107/) (2024)
- [Real-Time Neural BRDF with Spherically Distributed Primitives](https://mlsanity.com/paper/2310.08332/) (2023)
- [Real-Time Neural Materials using Block-Compressed Features](https://mlsanity.com/paper/2311.16121/) (2023)
- [GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Textures](https://mlsanity.com/paper/2311.16581/) (2023)
- [Neural Product Importance Sampling via Warp Composition](https://mlsanity.com/paper/2409.18974/) (2024)
- [VideoMatGen: PBR Materials through Joint Generative Modeling](https://mlsanity.com/paper/2603.16566/) (2026)
- [Efficient Graphics Representation with Differentiable Indirection](https://mlsanity.com/paper/2309.08387/) (2023)
- [Implicit Neural Representation of Tileable Material Textures](https://mlsanity.com/paper/2402.02208/) (2024)
- [Neural Graphics Texture Compression Supporting Random Access](https://mlsanity.com/paper/2407.00021/) (2024)
- [Mesh Compression with Quantized Neural Displacement Fields](https://mlsanity.com/paper/2504.01027/) (2025)
- [Lattice-based Deep Neural Networks: Regularity and Tailored Regularization](https://mlsanity.com/paper/2603.02809/) (2026)
- [Improved Stochastic Texture Filtering Through Sample Reuse](https://mlsanity.com/paper/2504.05562/) (2025)
- [ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering](https://mlsanity.com/paper/2506.13814/) (2025)
- [Collaborative Texture Filtering](https://mlsanity.com/paper/2506.17770/) (2025)
- [Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environments](https://mlsanity.com/paper/2604.12625/) (2026)
- [PEPS: Positional Encoding Projected Sampling -- Extended](https://mlsanity.com/paper/2604.24167/) (2026)
- [VUDA: Enabling Controlled Spatial Sharing of Graphics and Compute on NVIDIA GPUs](https://mlsanity.com/paper/2605.01352/) (2026)
- [Neural Texture Compression using Hypernetworks](https://mlsanity.com/paper/2606.26913/) (2026)
- [Thread-Efficient Decoding for Neural Texture Compression](https://mlsanity.com/paper/2608.27888/) (2026)
- [PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decoding](https://mlsanity.com/paper/2609.09020/) (2026)

## Abstract (arXiv)

The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed for material textures. We unlock two more levels of detail, i.e., 16x more texels, using low bitrate compression, with image quality that is better than advanced image compression techniques, such as AVIF and JPEG XL. At the same time, our method allows on-demand, real-time decompression with random access similar to block texture compression on GPUs, enabling compression on disk and memory. The key idea behind our approach is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them. Finally, we use a custom training implementation to achieve practical compression speeds, whose performance surpasses that of general frameworks, like PyTorch, by an order of magnitude.