# Distilled Low Rank Neural Radiance Field with Quantization for Light Field Compression

arXiv: https://arxiv.org/abs/2208.00164 · HTML: https://mlsanity.com/paper/2208.00164/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 51 references that are in the map.
- First posted on arXiv 30 Jul 2022.

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

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [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)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [Training with Quantization Noise for Extreme Model Compression](https://mlsanity.com/paper/2004.07320/) (2020)
- [M-LVC: Multiple Frames Prediction for Learned Video Compression](https://mlsanity.com/paper/2004.10290/) (2020)
- [Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement](https://mlsanity.com/paper/2003.01966/) (2020)
- [Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model](https://mlsanity.com/paper/2006.13560/) (2020)
- [Improving Deep Video Compression by Resolution-adaptive Flow Coding](https://mlsanity.com/paper/2009.05982/) (2020)
- [Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework](https://mlsanity.com/paper/2107.12422/) (2021)
- [End-to-End Rate-Distortion Optimization for Bi-Directional Learned Video Compression](https://mlsanity.com/paper/2008.05028/) (2020)
- [OpenDVC: An Open Source Implementation of the DVC Video Compression Method](https://mlsanity.com/paper/2006.15862/) (2020)
- [End-to-End Learning for Video Frame Compression with Self-Attention](https://mlsanity.com/paper/2004.09226/) (2020)

## Built on by (most cited first, 5 of 5)

- [Compressing Explicit Voxel Grid Representations: fast NeRFs become also small](https://mlsanity.com/paper/2210.12782/) (2022)
- [On Quantizing Implicit Neural Representations](https://mlsanity.com/paper/2209.01019/) (2022)
- [D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations](https://mlsanity.com/paper/2403.19163/) (2024)
- [Squeeze3D: Extreme Neural Compression with Latent Space Bridging](https://mlsanity.com/paper/2506.07932/) (2025)
- [SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization](https://mlsanity.com/paper/2510.15775/) (2025)

## Abstract (arXiv)

We propose in this paper a Quantized Distilled Low-Rank Neural Radiance Field (QDLR-NeRF) representation for the task of light field compression. While existing compression methods encode the set of light field sub-aperture images, our proposed method learns an implicit scene representation in the form of a Neural Radiance Field (NeRF), which also enables view synthesis. To reduce its size, the model is first learned under a Low-Rank (LR) constraint using a Tensor Train (TT) decomposition within an Alternating Direction Method of Multipliers (ADMM) optimization framework. To further reduce the model's size, the components of the tensor train decomposition need to be quantized. However, simultaneously considering the optimization of the NeRF model with both the low-rank constraint and rate-constrained weight quantization is challenging. To address this difficulty, we introduce a network distillation operation that separates the low-rank approximation and the weight quantization during network training. The information from the initial LR-constrained NeRF (LR-NeRF) is distilled into a model of much smaller dimension (DLR-NeRF) based on the TT decomposition of the LR-NeRF. We then learn an optimized global codebook to quantize all TT components, producing the final QDLR-NeRF. Experimental results show that our proposed method yields better compression efficiency compared to state-of-the-art methods, and it additionally has the advantage of allowing the synthesis of any light field view with high quality.