Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation

• URL: http://arxiv.org/abs/2601.12252v1
• Date: Sun, 18 Jan 2026 04:13:09 GMT
• Title: Breaking Coordinate Overfitting: Geometry-Aware WiFi Sensing for Cross-Layout 3D Pose Estimation
• Authors: Songming Jia, Yan Lu, Bin Liu, Xiang Zhang, Peng Zhao, Xinmeng Tang, Yelin Wei, Jinyang Huang, Huan Yan, Zhi Liu,
• Abstract summary: 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.
• Score: 26.629874388669176
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: WiFi-based 3D human pose estimation offers a low-cost and privacy-preserving alternative to vision-based systems for smart interaction. However, existing approaches rely on visual 3D poses as supervision and directly regress CSI to a camera-based coordinate system. We find that this practice leads to coordinate overfitting: models memorize deployment-specific WiFi transceiver layouts rather than only learning activity-relevant representations, resulting in severe generalization failures. To address this challenge, we present PerceptAlign, the first geometry-conditioned framework for WiFi-based cross-layout pose estimation. PerceptAlign introduces a lightweight coordinate unification procedure that aligns WiFi and vision measurements in a shared 3D space using only two checkerboards and a few photos. Within this unified space, it encodes calibrated transceiver positions into high-dimensional embeddings and fuses them with CSI features, making the model explicitly aware of device geometry as a conditional variable. This design forces the network to disentangle human motion from deployment layouts, enabling robust and, for the first time, layout-invariant WiFi pose estimation. To support systematic evaluation, we construct the largest cross-domain 3D WiFi pose estimation dataset to date, comprising 21 subjects, 5 scenes, 18 actions, and 7 device layouts. Experiments 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. These results establish geometry-conditioned learning as a viable path toward scalable and practical WiFi sensing.

Related papers

• Graph-based 3D Human Pose Estimation using WiFi Signals [7.772045520373017]
  GraphPose-Fi is a graph-based framework that explicitly models skeletal topology for WiFi-based 3D human pose estimation.<n>Our proposed method significantly outperforms existing methods on the MM-Fi dataset in various settings.
  arXiv  Detail & Related papers  (2025-11-24T13:40:26Z)
• GBlobs: Local LiDAR Geometry for Improved Sensor Placement Generalization [58.36712538433696]
  This report outlines the top-ranking solution for RoboSense 2025: Track 3.<n>It achieves state-of-the-art performance on 3D object detection under various sensor placements.
  arXiv  Detail & Related papers  (2025-10-21T11:35:58Z)
• NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space [77.6067460464962]
  Monocular 3D Semantic Scene Completion (SSC) has garnered significant attention in recent years due to its potential to predict complex semantics and geometry shapes from a single image, requiring no 3D inputs. We identify several critical issues in current state-of-the-art methods, including the Feature Ambiguity of projected 2D features in the ray to the 3D space, the Pose Ambiguity of the 3D convolution, and the Imbalance in the 3D convolution across different depth levels. We devise a novel Normalized Device Coordinates scene completion network (NDC-Scene) that directly extends the 2
  arXiv  Detail & Related papers  (2023-09-26T02:09:52Z)
• Geometric-aware Pretraining for Vision-centric 3D Object Detection [77.7979088689944]
  We propose a novel geometric-aware pretraining framework called GAPretrain. GAPretrain serves as a plug-and-play solution that can be flexibly applied to multiple state-of-the-art detectors. We achieve 46.2 mAP and 55.5 NDS on the nuScenes val set using the BEVFormer method, with a gain of 2.7 and 2.1 points, respectively.
  arXiv  Detail & Related papers  (2023-04-06T14:33:05Z)
• DensePose From WiFi [86.61881052177228]
  We develop a deep neural network that maps the phase and amplitude of WiFi signals to UV coordinates within 24 human regions. Our model can estimate the dense pose of multiple subjects, with comparable performance to image-based approaches.
  arXiv  Detail & Related papers  (2022-12-31T16:48:43Z)
• 3D Human Mesh Construction Leveraging Wi-Fi [6.157977673335047]
  Wi-Mesh is a vision-based 3D human mesh construction system. System uses WiFi to visualize the shape and deformations of the human body.
  arXiv  Detail & Related papers  (2022-10-20T01:58:27Z)
• Progressive Coordinate Transforms for Monocular 3D Object Detection [52.00071336733109]
  We propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations. In this paper, we propose a novel and lightweight approach, dubbed em Progressive Coordinate Transforms (PCT) to facilitate learning coordinate representations.
  arXiv  Detail & Related papers  (2021-08-12T15:22:33Z)
• WiCluster: Passive Indoor 2D/3D Positioning using WiFi without Precise Labels [0.0]
  We introduce WiCluster, a new machine learning (ML) approach for passive indoor positioning using radio frequency (RF) channel state information (CSI) WiCluster can predict both a zone-level position and a precise 2D or 3D position, without using any precise position labels during training.
  arXiv  Detail & Related papers  (2021-05-31T12:09:46Z)
• From Point to Space: 3D Moving Human Pose Estimation Using Commodity WiFi [21.30069619479767]
  We present Wi-Mose, the first 3D moving human pose estimation system using commodity WiFi. We fuse the amplitude and phase into Channel State Information (CSI) images which can provide both pose and position information. Experimental results show that Wi-Mose can localize key-point with 29.7mm and 37.8mm Procrustes analysis Mean Per Joint Position Error (P-MPJPE) in the Line of Sight (LoS) and Non-Line of Sight (NLoS) scenarios.
  arXiv  Detail & Related papers  (2020-12-28T02:27:26Z)
• Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training [3.8073142980733]
  We propose a novel framework for monocular 3D objects detection using only RGB images, called KM3D-Net. We design a fully convolutional model to predict object keypoints, dimension, and orientation, and then combine these estimations with perspective geometry constraints to compute position attribute.
  arXiv  Detail & Related papers  (2020-09-02T00:51:51Z)
• ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection [69.68263074432224]
  We present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in RGB images for more accurate disparity estimation, we introduce a conceptually straight-forward module -- adaptive zooming.
  arXiv  Detail & Related papers  (2020-03-01T17:18:08Z)

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.