Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Xingyu, Zhang, Xinyu, Zheng, Kai, Fang, Xinmin, Li, Tzu-Mao, Lu, Chris Xiaoxuan, Li, Zhengxiong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914408280621056
author Chen, Xingyu
Zhang, Xinyu
Zheng, Kai
Fang, Xinmin
Li, Tzu-Mao
Lu, Chris Xiaoxuan
Li, Zhengxiong
author_facet Chen, Xingyu
Zhang, Xinyu
Zheng, Kai
Fang, Xinmin
Li, Tzu-Mao
Lu, Chris Xiaoxuan
Li, Zhengxiong
contents Digital twins, virtual simulated replicas of physical scenes, are transforming system design across industries. However, their potential in radio frequency (RF) systems has been limited by the non-differentiable nature of conventional RF simulators. The visibility of propagation paths causes severe discontinuities, and differentiable rendering techniques from computer graphics cannot easily transfer due to point-source antennas and dominant specular reflections. In this paper, we present RFDT, a physically based differentiable RF simulation framework that enables gradient-based interaction between virtual and physical worlds. RFDT resolves discontinuities with a physically grounded edge-diffraction transition function, and mitigates non-convexity from Fourier-domain processing through a signal domain transform surrogate. Our implementation demonstrates RFDT's ability to accurately reconstruct digital twins from real RF measurements. Moreover, RFDT can augment diverse downstream applications, such as test-time adaptation of machine learning-based RF sensing and physically constrained optimization of communication systems.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18026
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin
Chen, Xingyu
Zhang, Xinyu
Zheng, Kai
Fang, Xinmin
Li, Tzu-Mao
Lu, Chris Xiaoxuan
Li, Zhengxiong
Signal Processing
Graphics
Machine Learning
Digital twins, virtual simulated replicas of physical scenes, are transforming system design across industries. However, their potential in radio frequency (RF) systems has been limited by the non-differentiable nature of conventional RF simulators. The visibility of propagation paths causes severe discontinuities, and differentiable rendering techniques from computer graphics cannot easily transfer due to point-source antennas and dominant specular reflections. In this paper, we present RFDT, a physically based differentiable RF simulation framework that enables gradient-based interaction between virtual and physical worlds. RFDT resolves discontinuities with a physically grounded edge-diffraction transition function, and mitigates non-convexity from Fourier-domain processing through a signal domain transform surrogate. Our implementation demonstrates RFDT's ability to accurately reconstruct digital twins from real RF measurements. Moreover, RFDT can augment diverse downstream applications, such as test-time adaptation of machine learning-based RF sensing and physically constrained optimization of communication systems.
title Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin
topic Signal Processing
Graphics
Machine Learning
url https://arxiv.org/abs/2603.18026