Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
This paper introduces GeRaF 2.0, a unified framework integrating Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) neural geometry reconstruction, leveraging LoS geometry to guide RF propagation for stable and physically consistent 3D reconstruction of hidden scenes, achieving state-of-the-art results.
Article intelligence
Key points
- RF signals can penetrate occlusions but suffer from low resolution and noise.
- Existing NLoS reconstruction methods ignore LoS constraints, causing unstable optimization and surface ambiguity.
- GeRaF 2.0 integrates LoS priors with neural fields for physically consistent reconstruction of visible and hidden geometry.
- The method achieves state-of-the-art performance in RF-based geometry reconstruction.
Why it matters
This matters because RF signals can penetrate occlusions but suffer from low resolution and noise.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.29098] Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
[Submitted on 27 May 2026]
Title:Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
View a PDF of the paper titled Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals, by Jiachen Lu and 2 other authors
View PDF HTML (experimental)
Abstract:Reconstructing object geometry from radio frequency (RF) signals is fundamentally challenging due to the lensless imaging nature of RF sensing, which leads to low spatial resolution and high noise. Unlike light signals, RF signals can penetrate occlusions and thus capture information about hidden scenes. Existing Non-Line-of-Sight (NLoS) 3D neural reconstruction methods can recover coarse surfaces inside enclosed environments but often suffer from unstable optimization, noisy surface geometry, and surface ambiguity, failing to produce accurate zero-level sets from the signed distance field (SDF). These limitations largely stem from neglecting the role of Line-of-Sight (LoS) geometry outside the enclosed region, which provides valuable physical constraints for modeling signal propagation. In this paper, we introduce a Unified LoS and NLoS neural geometry reconstruction framework GeRaF 2.0 that leverages the outside LoS geometry to model and guide RF propagation from the LoS region into the NLoS region. By integrating visual LoS priors into the neural field formulation, GeRaF 2.0 achieves stable training and physically consistent reconstruction of both visible and hidden geometry, setting a new state-of-the-art in RF-based geometry reconstruction.
Comments: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.29098 [cs.CV]
(or arXiv:2605.29098v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.29098
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Jiachen Lu [view email] [v1] Wed, 27 May 2026 20:58:41 UTC (7,199 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals, by Jiachen Lu and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)