# SINR: Sparsity Driven Compressed Implicit Neural Representations

arXiv: https://arxiv.org/abs/2503.19576 · HTML: https://mlsanity.com/paper/2503.19576/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 46 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 17 of 17)

- [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)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules](https://mlsanity.com/paper/2001.01568/) (2020)
- [Lossy Image Compression with Compressive Autoencoders](https://mlsanity.com/paper/1703.00395/) (2017)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [WIRE: Wavelet Implicit Neural Representations](https://mlsanity.com/paper/2301.05187/) (2023)
- [Implicit Neural Representations for Image Compression](https://mlsanity.com/paper/2112.04267/) (2021)
- [Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs](https://mlsanity.com/paper/2111.15135/) (2021)
- [Enhanced Invertible Encoding for Learned Image Compression](https://mlsanity.com/paper/2108.03690/) (2021)
- [COIN++: Neural Compression Across Modalities](https://mlsanity.com/paper/2201.12904/) (2022)
- [SHACIRA: Scalable HAsh-grid Compression for Implicit Neural Representations](https://mlsanity.com/paper/2309.15848/) (2023)
- [BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fields](https://mlsanity.com/paper/2306.03000/) (2023)
- [Improved Generalization of Weight Space Networks via Augmentations](https://mlsanity.com/paper/2402.04081/) (2024)
- [Jpeg Image Compression Using Discrete Cosine Transform - A Survey](https://mlsanity.com/paper/1405.6147/) (2014)
- [When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data](https://mlsanity.com/paper/2005.10940/) (2020)
- [An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU](https://mlsanity.com/paper/1902.07385/) (2019)

## Built on by (most cited first, 3 of 3)

- [Implicit Neural Representations: A Signal Processing Perspective](https://mlsanity.com/paper/2604.15047/) (2026)
- [Big2Small: A Unifying Neural Network Framework for Model Compression](https://mlsanity.com/paper/2603.29768/) (2026)
- [What Cohort INRs Encode and Where to Freeze Them](https://mlsanity.com/paper/2605.08298/) (2026)

## Abstract (arXiv)

Implicit Neural Representations (INRs) are increasingly recognized as a versatile data modality for representing discretized signals, offering benefits such as infinite query resolution and reduced storage requirements. Existing signal compression approaches for INRs typically employ one of two strategies: 1. direct quantization with entropy coding of the trained INR; 2. deriving a latent code on top of the INR through a learnable transformation. Thus, their performance is heavily dependent on the quantization and entropy coding schemes employed. In this paper, we introduce SINR, an innovative compression algorithm that leverages the patterns in the vector spaces formed by weights of INRs. We compress these vector spaces using a high-dimensional sparse code within a dictionary. Further analysis reveals that the atoms of the dictionary used to generate the sparse code do not need to be learned or transmitted to successfully recover the INR weights. We demonstrate that the proposed approach can be integrated with any existing INR-based signal compression technique. Our results indicate that SINR achieves substantial reductions in storage requirements for INRs across various configurations, outperforming conventional INR-based compression baselines. Furthermore, SINR maintains high-quality decoding across diverse data modalities, including images, occupancy fields, and Neural Radiance Fields.