R1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments

Xudong Yuan; Ruyun Xu; Jingtai Yang; Xianzheng Sun

cs.AIOct 4, 2026

R1A-PC: Physics-Guided Electromagnetic Inversion of Three-Dimensional Human Point Clouds in Complex Static Environments

Authors: Xudong Yuan, Ruyun Xu, Jingtai Yang, Xianzheng Sun

Organizations: School of Mathematics and Statistics, Changchun University of Science and Technology, Changchun, China.

Abstract

Recovering three-dimensional human geometry from electromagnetic measure?ments in a complex static environment is difficult because strong multipath responses from walls, floors, and other objects obscure the weak target per?turbation. We propose R1A-PC, a physics-guided method that reconstructs a 2048-point human cloud from paired complex fields measured with and without the target. Complex background subtraction emphasizes target-induced ampli?tude and phase changes, while the background field remains available as an environmental condition. A frequency-balanced discrete Born adjoint produces a three-dimensional spatial knowledge map. At each of two bounded deformation stages, the decoder combines complex measurement features, background fea?tures, and multiscale physical features queried at the current point coordinates; the second stage queries again after the first coordinate update. We analyze the residual of paired subtraction, the weighted normal-operator structure of the raw adjoint, and the feasible set of the predicted cloud. In a held-out background generated by full-wave simulation under a fixed acquisition geometry, R1A-PC obtains a squared Chamfer distance of 0.001434 m2 and an F-score of 0.963080 at 0.05 m. Compared with TopNet, the Chamfer distance decreases by 70.28%. Removing physical guidance or background subtraction increases the Chamfer distance by 242.06% or 241.18%, respectively. Experiments across background layouts and poses support the complementary roles of paired subtraction and position-dependent adjoint features.

Figures & tables

Figure 1: Three-dimensional electromagnetic acquisition geometry in a complex static environment. The env_004 example shows the DOI, four transmitters, twelve receiver locations, walls, static objects, and the human mesh; coordinates are in metres

Figure 2: R1A-PC architecture. Paired complex responses yield measurement, background, and adjoint spatial conditions. Multiscale queries at current point locations drive two bounded deformation stages to output a 2048-point human cloud

Figure 3: Two-stage point-cloud evolution for four fixed env_003 samples. Columns show standing, raised arm, bent torso, and side-facing poses; rows show stage P1, stage P2, and ground truth. All panels use the same coordinate limits, orthographic camera, point size, and height color scale

Environment	Static structure	Samples	Role
env_000	Floor	640	Training
env_001	Floor, two walls	640	Training
env_002	Floor, three objects	640	Training
env_003	Floor, two walls, four objects	570	Validation
env_004	Floor, two walls, four objects	500	Main test
env_005	Floor, two walls, four objects	70	Extended test

Table 1: Environment structure and data split. Counts are the samples included in each set.

	Overall geometry		Threshold coverage		Location and tail error
Method	CD-L2 $\downarrow$	Root-CD $\downarrow$	[email protected] $\uparrow$	[email protected] $\uparrow$	Centroid $\downarrow$	H95 $\downarrow$
Direct Born adjoint	$0.544516$	$0.737076$	$0.040135$	$0.162922$	$0.264834$	$0.975135$
Data-only TopNet	$0.004825$	$0.069099$	$0.188703$	$0.755998$	$0.155409$	$0.092107$
R1A-PC	$\mathbf{0.001434}$	$\mathbf{0.037753}$	$\mathbf{0.449782}$	$\mathbf{0.963080}$	$\mathbf{0.025276}$	$\mathbf{0.045617}$

Table 2: Method comparison on the principal test environment env_004. Trainable methods report means over three random seeds. The best mean for each metric is bold and shaded. CD-L2 is in m 2 ; Root-CD, centroid error, and H95 are in m.

Figure 4: Qualitative comparison for four env_003 poses. Rows show standing, raised arm, bent torso, and side-facing poses; columns show ground truth, Born adjoint, data-only TopNet, and R1A-PC. Colour encodes height $z$ . All panels use metric coordinates, common DOI limits, an orthographic camera, and the same point size

Figure 5: Seven extended poses in env_005. The upper row shows ground truth and the lower row R1A-PC. Columns show both arms raised, one arm extended forward, slight forward lean, standing lunge, natural sitting, forward-leaning sitting, and one-knee kneeling

Figure 6: Reconstruction-error distributions for 500 test targets in env_004. (a) Target-level empirical cumulative distributions of CD-L2 for the Born adjoint, data-only TopNet, and R1A-PC. (b) Target-level differences in CD-L2 between R1A-PC and TopNet; the zero line denotes equal errors

	Reconstruction quality			Relative change
Method	CD-L2 $\downarrow$	[email protected] $\uparrow$	H95 $\downarrow$	$\Delta$ CD-L2
Without physical guidance	$0.004907$	$0.763553$	$0.092685$	$242.06$
Without background subtraction	$0.004894$	$0.763412$	$0.092544$	$241.18$
Without cross-environment consistency	$0.001459$	$0.962987$	$0.045780$	$1.7$
R1A-PC	$\mathbf{0.001434}$	$\mathbf{0.963080}$	$\mathbf{0.045617}$	$0.0$

Table 3: Component ablations. Values are means of three independent trainings; relative CD-L2 changes use complete R1A-PC as the reference. CD-L2 is in m 2 and H95 in m.

	Overall accuracy		Location and tail error
Environment	CD-L2 $\downarrow$	[email protected] $\uparrow$	Centroid $\downarrow$	H95 $\downarrow$
env_002	$0.001210$	$0.976085$	$0.023693$	$0.041576$
env_003	$0.001592$	$0.950150$	$0.029864$	$0.049623$
env_004	$0.001434$	$0.963080$	$0.025276$	$0.045617$

Table 4: R1A-PC reconstruction results on three background levels; means of three independent trainings. CD-L2 is in m 2 and centroid error and H95 are in m.

	New-environment pose reconstruction
Method	CD-L2 $\downarrow$	[email protected] $\uparrow$	H95 $\downarrow$
Direct Born adjoint	$0.608902$	$0.143379$	$1.018$
Data-only TopNet	$0.008265$	$0.621074$	$0.114149$
R1A-PC	$\mathbf{0.004845}$	$\mathbf{0.863498}$	$\mathbf{0.092827}$

Table 5: Mean performance over seven pose groups in the new environment env_005. Trainable methods report means across three random seeds. CD-L2 is in m 2 and H95 in m.

	Model size		Inference cost
Method	Parameters	Output points	Time $\downarrow$	Memory $\downarrow$
Direct Born adjoint	$0$	$2\,048$	$29.803$	$140.3$
Data-only TopNet	$1\,029\,645$	$2\,048$	$2.164$	$16.8$
R1A-PC	$1\,114\,023$	$2\,048$	$6.460$	$68.3$

Table 6: Computational efficiency on an NVIDIA GeForce RTX 4060 Laptop GPU. Times are mean milliseconds per sample after input construction; peak memory is in MiB.

Explore similar work

TAP3D: Thermal-Assisted 3D Human Point Clouds
Oct 8, 2026Xie Zhang, Chengxiao Li, Xuan Liu +1
UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound
Sep 11, 2026Weiying Chen, Yuchong Gao, Siyuan Li +3Physics-Informed Generative Modeling Point Cloud Completion
University of Alberta, Edmonton, AB, Canada
GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals
May 27, 2026Jiachen Lu, Hailan Shanbhag, Haitham Al HassaniehImplicit Neural Representations 3D Reconstruction
École Polytechnique Fédérale de Lausanne (EPFL)

Oct 8, 2026, cs.CVJ/K move · Enter open · S save

TAP3D: Thermal-Assisted 3D Human Point Clouds

Xie Zhang, Chengxiao Li, Xuan Liu, Chenshu Wu

Open paper AskPDF arXiv

Human body point clouds are a versatile representation for AI-enabled human sensing. However, existing methods using LiDAR, radar, and depth cameras suffer from inherent drawbacks in high cost, sparse reconstruction, and privacy concerns, etc. In this paper, we exploit low-cost thermal arrays and present TAP3D, the first system to reconstruct 3D human point clouds from body heat signatures, offering significant advantages in cost, density, human sensitivity, and privacy. To overcome major challenges in depth estimation, thermal interference, and multi-person separation, we propose a novel physics-informed design, which integrates a forward thermal physics model with two distinct modules: multi-primitive estimation for self-supervised joint recovery of depth and other thermal properties, and geometric perspective fusion for suppressing interference and disentangling multiple people. We implement TAP3D using a single commodity thermal array sensor and build a large-scale dataset (160K samples, 8 environments, 11 users) for evaluation. TAP3D achieves remarkable accuracy for dense point cloud generation, enabling downstream tasks like fall detection (91.46%), indoor tracking (21.86 cm MAE), and human mesh recovery (4.87 cm error). By transforming body heat into point clouds for the first time, TAP3D pioneers a new paradigm for privacy-first, fully passive human sensing for many applications. TAP3D is open-sourced at https://github.com/aiot-lab/TAP3D.

Abstract

Explore similar work

TAP3D: Thermal-Assisted 3D Human Point Clouds

UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound

GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals