# 3D Scene Compression through Entropy Penalized Neural Representation Functions

arXiv: https://arxiv.org/abs/2104.12456 · HTML: https://mlsanity.com/paper/2104.12456/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [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)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters](https://mlsanity.com/paper/1810.00440/) (2018)
- [Scalable Model Compression by Entropy Penalized Reparameterization](https://mlsanity.com/paper/1906.06624/) (2019)
- [DSIC: Deep Stereo Image Compression](https://mlsanity.com/paper/1908.03631/) (2019)
- [Evaluation of 4D Light Field Compression Methods](https://mlsanity.com/paper/1905.07432/) (2019)

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

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023)
- [Implicit Neural Representations for Image Compression](https://mlsanity.com/paper/2112.04267/) (2021)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [An Introduction to Neural Data Compression](https://mlsanity.com/paper/2202.06533/) (2022)
- [Masked Wavelet Representation for Compact Neural Radiance Fields](https://mlsanity.com/paper/2212.09069/) (2022)
- [Compression with Bayesian Implicit Neural Representations](https://mlsanity.com/paper/2305.19185/) (2023)
- [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)
- [NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representation](https://mlsanity.com/paper/2404.02185/) (2024)
- [DaReNeRF: Direction-aware Representation for Dynamic Scenes](https://mlsanity.com/paper/2403.02265/) (2024)
- [Lossy Neural Compression for Geospatial Analytics: A Review](https://mlsanity.com/paper/2503.01505/) (2025)
- [ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimization](https://mlsanity.com/paper/2311.14208/) (2023)
- [CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis](https://mlsanity.com/paper/2404.04913/) (2024)
- [Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention](https://mlsanity.com/paper/2304.00335/) (2023)
- [CAwa-NeRF: Instant Learning of Compression-Aware NeRF Features](https://mlsanity.com/paper/2310.14695/) (2023)
- [SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field](https://mlsanity.com/paper/2402.16366/) (2024)
- [Neural NeRF Compression](https://mlsanity.com/paper/2406.08943/) (2024)
- [Plenoptic PNG: Real-Time Neural Radiance Fields in 150 KB](https://mlsanity.com/paper/2409.15689/) (2024)
- [Implicit Neural Compression of Point Clouds](https://mlsanity.com/paper/2412.10433/) (2024)
- [TeSO: Representing and Compressing 3D Point Cloud Scenes with Textured Surfel Octree](https://mlsanity.com/paper/2508.07083/) (2025)
- [DaRePlane: Direction-aware Representations for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2410.14169/) (2024)
- [Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors](https://mlsanity.com/paper/2609.33969/) (2026)

## Abstract (arXiv)

Some forms of novel visual media enable the viewer to explore a 3D scene from arbitrary viewpoints, by interpolating between a discrete set of original views. Compared to 2D imagery, these types of applications require much larger amounts of storage space, which we seek to reduce. Existing approaches for compressing 3D scenes are based on a separation of compression and rendering: each of the original views is compressed using traditional 2D image formats; the receiver decompresses the views and then performs the rendering. We unify these steps by directly compressing an implicit representation of the scene, a function that maps spatial coordinates to a radiance vector field, which can then be queried to render arbitrary viewpoints. The function is implemented as a neural network and jointly trained for reconstruction as well as compressibility, in an end-to-end manner, with the use of an entropy penalty on the parameters. Our method significantly outperforms a state-of-the-art conventional approach for scene compression, achieving simultaneously higher quality reconstructions and lower bitrates. Furthermore, we show that the performance at lower bitrates can be improved by jointly representing multiple scenes using a soft form of parameter sharing.