mlsanityData to 14 Oct 2026

Random-Access Neural Compression of Material Textures

arXiv 2305.17105 ↗First posted 26 May 2023cs.GR cs.CVcited by 23

Not on the map. Why?

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.

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

32 of 97 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2017Neural Discrete Representation Learningcited by 4,712
  7. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  8. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  9. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  10. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  11. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  12. 2019Searching for MobileNetV3cited by 1,994
20 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2017Deep Image Priorcited by 1,098
  4. 2018Variational image compression with a scale hyperpriorcited by 935
  5. 2016End-to-end Optimized Image Compressioncited by 696
  6. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  7. 2017The Perception-Distortion Tradeoffcited by 587
  8. 2021Advances in Neural Renderingcited by 365
  9. 2020High-Fidelity Generative Image Compressioncited by 338
  10. 2017Lossy Image Compression with Compressive Autoencoderscited by 294
  11. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  12. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  13. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  14. 2020Nonlinear Transform Codingcited by 136
  15. 2017Real-Time Adaptive Image Compressioncited by 130
  16. 2022Variable Bitrate Neural Fieldscited by 117
  17. 2021Real-time Neural Radiance Caching for Path Tracingcited by 91
  18. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  19. 2017Guetzli: Perceptually Guided JPEG Encodercited by 6
  20. 2021Passing Multi-Channel Material Textures to a 3-Channel Losscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 5; 2026: 8.

23 papers.

Sort:

By area:

  1. 2024Image-GS: Content-Adaptive Image Representation via 2D Gaussianscited by 35
  2. 2023Compact Neural Graphics Primitives with Learned Hash Probingcited by 19
  3. 2025Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splattingcited by 18
  4. 2024Filtering After Shading With Stochastic Texture Filteringcited by 5
  5. 2023Real-Time Neural BRDF with Spherically Distributed Primitivescited by 4
  6. 2023Real-Time Neural Materials using Block-Compressed Featurescited by 4
  7. 2023GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Texturescited by 3
  8. 2024Neural Product Importance Sampling via Warp Compositioncited by 3
  9. 2026VideoMatGen: PBR Materials through Joint Generative Modelingcited by 3
  10. 2023Efficient Graphics Representation with Differentiable Indirectioncited by 2
  11. 2024Implicit Neural Representation of Tileable Material Texturescited by 2
  12. 2024Neural Graphics Texture Compression Supporting Random Accesscited by 2
11 more
  1. 2025Mesh Compression with Quantized Neural Displacement Fieldscited by 2
  2. 2026Lattice-based Deep Neural Networks: Regularity and Tailored Regularizationcited by 2
  3. 2025Improved Stochastic Texture Filtering Through Sample Reusecited by 1
  4. 2025ReFrame: Layer Caching for Accelerated Inference in Real-Time Renderingcited by 0
  5. 2025Collaborative Texture Filteringcited by 0
  6. 2026Neural Dynamic GI: Random-Access Neural Compression for Temporal Lightmaps in Dynamic Lighting Environmentscited by 0
  7. 2026PEPS: Positional Encoding Projected Sampling -- Extendedcited by 0
  8. 2026VUDA: Enabling Controlled Spatial Sharing of Graphics and Compute on NVIDIA GPUscited by 0
  9. 2026Neural Texture Compression using Hypernetworkscited by 0
  10. 2026Thread-Efficient Decoding for Neural Texture Compressioncited by 0
  11. 2026PIC: Revisiting INR for Image Coding with Fast Encoding and Sub-Millisecond Decodingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond UV Mapping: Mesh Texture Compression via Surface-Aligned Texture Fields
  2. 2026Rate-Adaptive One-Step Diffusion Compression for AIGC Images
  3. 2026Compression of 3D Gaussian Splatting Data Using GPU-friendly Graphics Texture Coding
  4. 2024Infinite Texture: Text-guided High Resolution Diffusion Texture Synthesis
  5. 2023You Can Mask More For Extremely Low-Bitrate Image Compression
  6. 2023Towards image compression with perfect realism at ultra-low bitrates
  7. 2024LDM: Large Tensorial SDF Model for Textured Mesh Generation
  8. 2021COIN: COmpression with Implicit Neural representations