RePos: Relative-to-Absolute Output Factorization for Cross-Environment WiFi-Based 3D Human Pose Estimation

• URL: http://arxiv.org/abs/2607.02986v1
• Date: Fri, 03 Jul 2026 05:49:12 GMT
• Title: RePos: Relative-to-Absolute Output Factorization for Cross-Environment WiFi-Based 3D Human Pose Estimation
• Abstract summary: Device-free 3D human pose estimation using commodity WiFi Channel State Information (CSI) enables privacy-preserving and illumination-robust human sensing.<n>We propose RePos, a factorized framework that separates root-relative pose estimation from root localization.<n>Under the strict MM-Fi cross-environment protocol, RePos achieves MPJPEs of 254.4-296.1 mm, a 10-21% reduction over existing WiFi-based methods.
• Score: 15.398789370857786
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Device-free 3D human pose estimation using commodity WiFi Channel State Information (CSI) enables privacy-preserving and illumination-robust human sensing, but its deployment is limited by poor cross-environment generalization. Unlike images, CSI measurements do not have a spatially localized correspondence to body parts and are heavily affected by multipath propagation, causing models that regress absolute poses to entangle body structure with environment-specific location cues. Within a single environment this coupling is benign: an end-to-end absolute-pose variant, RePos-D, already achieves state-of-the-art accuracy on Person-in-WiFi-3D (86.9 mm MPJPE, a 3.4% gain over the previous best WiFi method, DT-Pose). Across environments, however, the same model overfits position and suffers significant performance degradation. We therefore propose RePos, a factorized framework that separates root-relative pose estimation from root localization. By preventing absolute-pose supervision from affecting the structure branch, RePos learns environment-invariant pose representations. Specifically, it groups CSI features into body-part-aware latent tokens that skeleton-guided modeling refines into the pose, while a separate amplitude-based network estimates the root position through a differentiable spatial-decomposition module. Under the strict MM-Fi cross-environment protocol, RePos achieves MPJPEs of 254.4-296.1 mm, a 10-21% reduction over existing WiFi-based methods. The improvement remains consistent across activity protocols, leave-one-environment-out splits, and leakage-free few-shot transfer. Analysis of the learned features shows that relative-pose representations remain largely position-agnostic, while root localization retains environment dependence, indicating distinct generalization behavior for structure and localization.

Related papers

• DisPOSE: Projected Polystochastic Diffusion for Self-Supervised Multi-View 3D Human Pose Estimation [58.47973015036709]
  DisPOSE is a self-supervised framework that approximates the inherently discrete multi-view person-assignment problem.<n>By employing differentiable Sinkhorn projections during denoising, our model learns to guide solutions toward valid and feasible assignments.<n>The proposed approach outperforms current state-of-the-art self-supervised methods on standard datasets.
  arXiv  Detail & Related papers  (2026-06-05T16:14:39Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation [26.629874388669176]
  We present PerceptAlign, the first geometry-conditioned framework for WiFi-based cross-domain pose estimation.<n>We show that PerceptAlign reduces in-domain error by 12.3% and cross-domain error by more than 60% compared to state-of-the-art baselines.<n>These results establish geometry-conditioned learning as a viable path toward scalable and practical WiFi sensing.
  arXiv  Detail & Related papers  (2026-01-18T04:13:09Z)
• VST-Pose: A Velocity-Integrated Spatiotem-poral Attention Network for Human WiFi Pose Estimation [10.371863139473456]
  VST-Pose is a novel framework for accurate pose estimation using WiFi channel state information.<n>Our method achieves 92.2% accuracy on the PCK@50 metric, outperforming existing methods by 8.3% in PCK@50 on the self-collected dataset.<n>The proposed system provides a reliable and privacy-aware solution for continuous human motion analysis in indoor environments.
  arXiv  Detail & Related papers  (2025-07-13T15:11:18Z)
• Unsupervised Cross-Domain 3D Human Pose Estimation via Pseudo-Label-Guided Global Transforms [28.40521894200745]
  We propose a novel framework that conducts global transformations between pose positions.<n>A Pose Augmentor is incorporated to address variations in human posture and body size.<n>The proposed method outperforms state-of-the-art approaches and even outperforms the target-trained model.
  arXiv  Detail & Related papers  (2025-04-17T06:57:20Z)
• PIDLoc: Cross-View Pose Optimization Network Inspired by PID Controllers [7.582581416640314]
  PIDLoc is a novel cross-view pose optimization approach inspired by the proportional-integral-derivative (PID) controller.<n>The PIDLoc achieves state-of-the-art performance in cross-view pose estimation for the KITTI dataset, reducing position error by $37.8%$ compared with the previous state-of-the-art.
  arXiv  Detail & Related papers  (2025-03-04T08:24:08Z)
• Exploiting Aggregation and Segregation of Representations for Domain Adaptive Human Pose Estimation [50.31351006532924]
  Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc.<n>It suffers from the lack of labeled diverse real-world datasets due to the time- and labor-intensive annotation.<n>We introduce a novel framework that capitalizes on both representation aggregation and segregation for domain adaptive human pose estimation.
  arXiv  Detail & Related papers  (2024-12-29T17:59:45Z)
• AdaPose: Towards Cross-Site Device-Free Human Pose Estimation with Commodity WiFi [34.06785676288187]
  WiFi-based pose estimation is a technology with great potential for the development of smart homes and metaverse avatar generation. We propose a domain adaptation algorithm, AdaPose, designed specifically for weakly-supervised WiFi-based pose estimation. We conduct extensive experiments on domain adaptation in two different scenes using our self-collected pose estimation dataset.
  arXiv  Detail & Related papers  (2023-09-29T04:16:33Z)
• Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance [48.39751410262664]
  ArtEq is a part-based SE(3)-equivariant neural architecture for SMPL model estimation from point clouds. Experimental results show that ArtEq generalizes to poses not seen during training, outperforming state-of-the-art methods by 44% in terms of body reconstruction accuracy.
  arXiv  Detail & Related papers  (2023-04-20T17:58:26Z)
• Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation [63.199549837604444]
  3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. We cast 3D pose learning as a self-supervised adaptation problem that aims to transfer the task knowledge from a labeled source domain to a completely unpaired target. We evaluate different self-adaptation settings and demonstrate state-of-the-art 3D human pose estimation performance on standard benchmarks.
  arXiv  Detail & Related papers  (2022-04-05T03:52:57Z)
• Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration [67.69257782645789]
  We propose piecewise transformation fields that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We show that fitting parametric models with poses by our network results in much better registration quality, especially for extreme poses.
  arXiv  Detail & Related papers  (2021-04-16T15:16:09Z)

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.