# Neural 3D Scene Compression via Model Compression

arXiv: https://arxiv.org/abs/2105.03120 · HTML: https://mlsanity.com/paper/2105.03120/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 7 May 2021.

## Builds on (most cited first, 16 of 16)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [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)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [A Volumetric Approach to Point Cloud Compression](https://mlsanity.com/paper/1810.00484/) (2018)
- [Neural Network Compression for Noisy Storage Devices](https://mlsanity.com/paper/2102.07725/) (2021)
- [Image compression optimized for 3D reconstruction by utilizing deep neural networks](https://mlsanity.com/paper/2003.12618/) (2020)

## Built on by (most cited first, 7 of 7)

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [On Quantizing Implicit Neural Representations](https://mlsanity.com/paper/2209.01019/) (2022)
- [LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks](https://mlsanity.com/paper/2111.08988/) (2021)
- [Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration](https://mlsanity.com/paper/2504.00950/) (2025)
- [Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention](https://mlsanity.com/paper/2304.00335/) (2023)
- [3D Compression Using Neural Fields](https://mlsanity.com/paper/2311.13009/) (2023)
- [Squeeze3D: Extreme Neural Compression with Latent Space Bridging](https://mlsanity.com/paper/2506.07932/) (2025)

## Abstract (arXiv)

Rendering 3D scenes requires access to arbitrary viewpoints from the scene. Storage of such a 3D scene can be done in two ways; (1) storing 2D images taken from the 3D scene that can reconstruct the scene back through interpolations, or (2) storing a representation of the 3D scene itself that already encodes views from all directions. So far, traditional 3D compression methods have focused on the first type of storage and compressed the original 2D images with image compression techniques. With this approach, the user first decodes the stored 2D images and then renders the 3D scene. However, this separated procedure is inefficient since a large amount of 2D images have to be stored. In this work, we take a different approach and compress a functional representation of 3D scenes. In particular, we introduce a method to compress 3D scenes by compressing the neural networks that represent the scenes as neural radiance fields. Our method provides more efficient storage of 3D scenes since it does not store 2D images -- which are redundant when we render the scene from the neural functional representation.