# Model-based Implicit Neural Representation for sub-wavelength Radio Localization

arXiv: https://arxiv.org/abs/2506.06387 · HTML: https://mlsanity.com/paper/2506.06387/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 57 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 28 of 28)

- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [Model-Based Deep Learning](https://mlsanity.com/paper/2012.08405/) (2020)
- [Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey](https://mlsanity.com/paper/2411.03688/) (2024)
- [Deep MIMO Detection](https://mlsanity.com/paper/1706.01151/) (2017)
- [Learning Radio Environments by Differentiable Ray Tracing](https://mlsanity.com/paper/2311.18558/) (2023)
- [mpNet: variable depth unfolded neural network for massive MIMO channel estimation](https://mlsanity.com/paper/2008.04088/) (2020)
- [A Comprehensive Survey of Machine Learning Based Localization with Wireless Signals](https://mlsanity.com/paper/2012.11171/) (2020)
- [Learn to Rapidly and Robustly Optimize Hybrid Precoding](https://mlsanity.com/paper/2301.00369/) (2023)
- [Radio Localization and Mapping with Reconfigurable Intelligent Surfaces](https://mlsanity.com/paper/1912.09401/) (2019)
- [Leveraging triplet loss and nonlinear dimensionality reduction for on-the-fly channel charting](https://mlsanity.com/paper/2204.13996/) (2022)
- [Efficient channel charting via phase-insensitive distance computation](https://mlsanity.com/paper/2104.13184/) (2021)
- [Efficient Deep Unfolding for SISO-OFDM Channel Estimation](https://mlsanity.com/paper/2210.06588/) (2022)
- [SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimation](https://mlsanity.com/paper/2306.02271/) (2023)
- [RF Fingerprinting and Deep Learning Assisted UE Positioning in 5G](https://mlsanity.com/paper/2001.00977/) (2020)
- [Optimizing Multicarrier Multiantenna Systems for LoS Channel Charting](https://mlsanity.com/paper/2310.03762/) (2023)
- [Semi-Supervised End-to-End Learning for Integrated Sensing and Communications](https://mlsanity.com/paper/2310.09940/) (2023)
- [Physically Parameterized Differentiable MUSIC for DoA Estimation with Uncalibrated Arrays](https://mlsanity.com/paper/2411.15144/) (2024)
- [A Soft Range Limited K-Nearest Neighbours Algorithm for Indoor Localization Enhancement](https://mlsanity.com/paper/1908.11480/) (2019)
- [Model-based learning for location-to-channel mapping](https://mlsanity.com/paper/2308.14370/) (2023)
- [Model-based Deep Learning for Beam Prediction based on a Channel Chart](https://mlsanity.com/paper/2312.02239/) (2023)
- [Towards Fine-Grained Indoor Localization based on Massive MIMO-OFDM System: Experiment and Analysis](https://mlsanity.com/paper/2103.14863/) (2021)
- [Tuning of Ray-Based Channel Model for 5G Indoor Industrial Scenarios](https://mlsanity.com/paper/2309.06101/) (2023)
- [Model-based learning for multi-antenna multi-frequency location-to-channel mapping](https://mlsanity.com/paper/2407.07719/) (2024)
- [Model-based Learning Network for 3-D Localization in mmWave Communications](https://mlsanity.com/paper/2103.11122/) (2021)
- [Efficient Ray-Tracing Channel Emulation in Industrial Environments: An Analysis of Propagation Model Impact](https://mlsanity.com/paper/2306.01408/) (2023)
- [From C-Band to mmWave-Band: Ray-Tracing-Assisted 5G-Based Indoor Positioning in Industrial Scenario](https://mlsanity.com/paper/2409.12624/) (2024)
- [Unsupervised Learning for Gain-Phase Impairment Calibration in ISAC Systems](https://mlsanity.com/paper/2410.04176/) (2024)
- [CSI Compression using Channel Charting](https://mlsanity.com/paper/2501.01431/) (2024)

## Abstract (arXiv)

The increasing deployment of large antenna arrays at base stations has significantly improved the spatial resolution and localization accuracy of radio-localization methods. However, traditional signal processing techniques struggle in complex radio environments, particularly in scenarios dominated by non line of sight (NLoS) propagation paths, resulting in degraded localization accuracy. Recent developments in machine learning have facilitated the development of machine learning-assisted localization techniques, enhancing localization accuracy in complex radio environments. However, these methods often involve substantial computational complexity during both the training and inference phases. This work extends the well-established fingerprinting-based localization framework by simultaneously reducing its memory requirements and improving its accuracy. Specifically, a model-based neural network is used to learn the location-to-channel mapping, and then serves as a generative neural channel model. This generative model augments the fingerprinting comparison dictionary while reducing the memory requirements. The proposed method outperforms fingerprinting baselines by achieving sub-wavelength localization accuracy, even in complex static NLoS environments. Remarkably, it offers an improvement by several orders of magnitude in localization accuracy, while simultaneously reducing memory requirements by an order of magnitude compared to classical fingerprinting methods.