Radiance-Field Reinforced Pretraining: Scaling Localization Models with Unlabeled Wireless Signals

• URL: http://arxiv.org/abs/2512.07309v1
• Date: Mon, 08 Dec 2025 08:52:08 GMT
• Title: Radiance-Field Reinforced Pretraining: Scaling Localization Models with Unlabeled Wireless Signals
• Authors: Guosheng Wang, Shen Wang, Lei Yang,
• Abstract summary: Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing.<n>We introduce Radiance-Field Reinforced Pretraining (RFRP)<n>This novel self-supervised pretraining framework couples a large localization model (LM) with a neural radio-frequency radiance field (RF-NeRF) in an asymmetrical autoencoder architecture.<n>We show that the RFRP-pretrained LM reduces localization error by over 40% compared to non-pretrained models and by 21% compared to those pretrained using supervised learning.
• Score: 5.688789306551577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learning has greatly enhanced localization accuracy and robustness, existing localization models still face major challenges in cross-scene generalization due to their reliance on scene-specific labeled data. To address this, we introduce Radiance-Field Reinforced Pretraining (RFRP). This novel self-supervised pretraining framework couples a large localization model (LM) with a neural radio-frequency radiance field (RF-NeRF) in an asymmetrical autoencoder architecture. In this design, the LM encodes received RF spectra into latent, position-relevant representations, while the RF-NeRF decodes them to reconstruct the original spectra. This alignment between input and output enables effective representation learning using large-scale, unlabeled RF data, which can be collected continuously with minimal effort. To this end, we collected RF samples at 7,327,321 positions across 100 diverse scenes using four common wireless technologies--RFID, BLE, WiFi, and IIoT. Data from 75 scenes were used for training, and the remaining 25 for evaluation. Experimental results show that the RFRP-pretrained LM reduces localization error by over 40% compared to non-pretrained models and by 21% compared to those pretrained using supervised learning.

Related papers

• RF-GPT: Teaching AI to See the Wireless World [48.294819966466044]
  Large language models (LLMs) and multimodal models have become powerful general-purpose reasoning systems.<n>RF-GPT is a radio-frequency language model (RFLM) that utilizes the visual encoders of multimodals to process and understand RF spectrograms.<n>A text-only LLM then converts these captions into RF-grounded instruction-answer pairs, yielding roughly 12,000 RF scenes and 25 million examples.
  arXiv  Detail & Related papers  (2026-02-16T15:24:56Z)
• Generative MIMO Beam Map Construction for Location Recovery and Beam Tracking [67.65578956523403]
  This paper proposes a generative framework to recover location labels directly from sparse channel state information (CSI) measurements.<n>Instead of directly storing raw CSI, we learn a compact low-dimensional radio map embedding and leverage a generative model to reconstruct the high-dimensional CSI.<n> Numerical experiments demonstrate that the proposed model can improve localization accuracy by over 30% and achieve a 20% capacity gain in non-line-of-sight (NLOS) scenarios.
  arXiv  Detail & Related papers  (2025-11-21T07:25:49Z)
• Rasterizing Wireless Radiance Field via Deformable 2D Gaussian Splatting [10.200300617390013]
  Modeling wireless radiance field (WRF) is fundamental to modern communication systems.<n>We propose SwiftWRF, a deformable 2D splatting framework that synthesizes WRF spectra at arbitrary positions.<n>Experiments on both real-world and synthetic indoor scenes demonstrate that SwiftWRF can reconstruct WRF up to 500x faster than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-15T09:36:45Z)
• DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform [3.44306950522716]
  We present DWTNeRF, a unified framework based on Instant-NGP's fast-training hash encoding.<n>It is coupled with regularization terms designed for few-shot NeRF, which operates on sparse training views.<n>Our approach encourages a re-thinking of current few-shot approaches for fast-converging implicit representations like INGP or 3DGS.
  arXiv  Detail & Related papers  (2025-01-22T04:53:12Z)
• Few-shot NeRF by Adaptive Rendering Loss Regularization [78.50710219013301]
  Novel view synthesis with sparse inputs poses great challenges to Neural Radiance Field (NeRF) Recent works demonstrate that the frequency regularization of Positional rendering can achieve promising results for few-shot NeRF. We propose Adaptive Rendering loss regularization for few-shot NeRF, dubbed AR-NeRF.
  arXiv  Detail & Related papers  (2024-10-23T13:05:26Z)
• RF-ULM: Ultrasound Localization Microscopy Learned from Radio-Frequency Wavefronts [7.652037892439504]
  Delay-and-sum beamforming leads to irreversible reduction of Radio-Frequency (RF) channel data. rich contextual information embedded within RF wavefronts offers great promise for guiding Deep Neural Networks (DNNs) in challenging localization scenarios. We propose to directly localize scatterers in RF channel data using learned feature channel shuffling, non-maximum suppression, and a semi-global convolutional block.
  arXiv  Detail & Related papers  (2023-10-02T18:41:23Z)
• MS-NeRF: Multi-Space Neural Radiance Fields [48.0367339199913]
  Existing Neural Radiance Fields (NeRF) methods suffer from the existence of reflective objects, often resulting in blurry rendering.<n>We propose a multi-space neural radiance field (MS-NeRF) that represents the scene using a group of feature fields in parallel sub-spaces.<n>Our approach significantly outperforms the existing single-space NeRF methods for rendering high-quality scenes.
  arXiv  Detail & Related papers  (2023-05-07T13:11:07Z)
• Re-ReND: Real-time Rendering of NeRFs across Devices [56.081995086924216]
  Re-ReND is designed to achieve real-time performance by converting the NeRF into a representation that can be efficiently processed by standard graphics pipelines. We find that Re-ReND can achieve over a 2.6-fold increase in rendering speed versus the state-of-the-art without perceptible losses in quality.
  arXiv  Detail & Related papers  (2023-03-15T15:59:41Z)
• One-shot Generative Distribution Matching for Augmented RF-based UAV Identification [0.0]
  This work addresses the challenge of identifying Unmanned Aerial Vehicles (UAV) using radiofrequency (RF) fingerprinting in limited RF environments. The complexity and variability of RF signals, influenced by environmental interference and hardware imperfections, often render traditional RF-based identification methods ineffective. One-shot generative methods for augmenting transformed RF signals offer a significant improvement in UAV identification.
  arXiv  Detail & Related papers  (2023-01-20T02:35:43Z)
• Disentangled Representation Learning for RF Fingerprint Extraction under Unknown Channel Statistics [77.13542705329328]
  We propose a framework of disentangled representation learning(DRL) that first learns to factor the input signals into a device-relevant component and a device-irrelevant component via adversarial learning. The implicit data augmentation in the proposed framework imposes a regularization on the RFF extractor to avoid the possible overfitting of device-irrelevant channel statistics. Experiments validate that the proposed approach, referred to as DR-RFF, outperforms conventional methods in terms of generalizability to unknown complicated propagation environments.
  arXiv  Detail & Related papers  (2022-08-04T15:46:48Z)
• RF Signal Classification with Synthetic Training Data and its Real-World Performance [0.0]
  This paper investigates the impact of different RF signal impairments modeled in synthetic training data with respect to the real-world performance. It achieves an accuracy of up to 95 % in real-world operation by using carefully designed synthetic training data only.
  arXiv  Detail & Related papers  (2022-06-26T20:47:33Z)
• Three-Way Deep Neural Network for Radio Frequency Map Generation and Source Localization [67.93423427193055]
  Monitoring wireless spectrum over spatial, temporal, and frequency domains will become a critical feature in beyond-5G and 6G communication technologies. In this paper, we present a Generative Adversarial Network (GAN) machine learning model to interpolate irregularly distributed measurements across the spatial domain.
  arXiv  Detail & Related papers  (2021-11-23T22:25:10Z)
• Spectro-Temporal RF Identification using Deep Learning [3.8137985834223507]
  WRIST is a Wideband, Real-time RF Identification system with Spectro-Temporal detection, framework and system. Our resulting deep learning model is capable to detect, classify, and precisely locate RF emissions in time and frequency. WRIST detector achieves 90 mean Average Precision even in extremely congested environment in the wild.
  arXiv  Detail & Related papers  (2021-07-11T19:02:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.