GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals
Quick Take
GeRaF introduces a novel approach for 3D geometry reconstruction from RF signals using neural implicit learning, overcoming challenges like occlusion and noise. It employs filter-based rendering, a physics-based volumetric pipeline, and lensless sampling to achieve millimeter-level accuracy in real-world environments.
Key Points
- GeRaF is the first method for near-range 3D reconstruction from RF signals.
- It addresses low resolution and noise inherent in RF sensing.
- The model introduces filter-based rendering to enhance signal quality.
- A physics-based volumetric rendering pipeline is implemented.
- GeRaF enables full-space sampling during training for improved accuracy.
Article Excerpt
From source RSS / original summaryarXiv:2605. 29097v1 Announce Type: new Abstract: GeRaF is the first method to use neural implicit learning for near-range 3D geometry reconstruction from radio frequency (RF) signals. Unlike RGB or LiDAR-based methods, RF sensing can see through occlusion but suffers from low resolution and noise due to its lensless imaging nature.
While lenses in RGB imaging constrain sampling to 1D rays, RF signals propagate through the entire space, introducing significant noise and leading to cubic complexity in volumetric rendering. Moreover, RF signals interact with surfaces via specular reflections, requiring fundamentally different modeling.
To address these challenges, GeRaF (1) introduces filter-based rendering to suppress irrelevant signals, (2) implements a physics-based RF volumetric rendering pipeline, and (3) proposes a novel lensless sampling and lensless alpha blending strategy that makes full-space sampling feasible during training.
By learning signed distance functions, reflectiveness, and signal power through MLPs and trainable parameters, GeRaF takes the first step towards reconstructing millimeter-level geometry from RF signals in real-world settings.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →Evi-Steer: Learning to Steer Biomedical Vision-Language Models through Efficient and Generalizable Evidential Tuning
Evi-Steer introduces a novel evidential tuning framework for BiomedCLIP, achieving 0.11% parameter updates while enhancing uncertainty-aware fine-tuning. It outperforms state-of-the-art methods across 15 biomedical imaging datasets, proving effective in few-shot learning and domain shifts for clinical applications.
