WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation

• URL: http://arxiv.org/abs/2607.11064v1
• Date: Mon, 13 Jul 2026 04:05:07 GMT
• Title: WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation
• Abstract summary: WiFi Channel State Information (CSI) enables privacy-preserving human pose sensing in camera-denied environments.<n>We propose WiFi-JEPA, a self-supervised framework that learns CSI-native representations by predicting masked latent embeddings.
• Score: 0.6416429054645992
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: WiFi Channel State Information (CSI) enables privacy-preserving human pose sensing in camera-denied environments, but existing WiFi-based pose estimators often fail under environment shifts and rely on costly camera-based annotation pipelines that limit scale. We propose WiFi-JEPA, a self-supervised framework that learns CSI-native representations by predicting masked latent embeddings instead of reconstructing raw CSI signals that may contain hardware-specific artifacts. WiFi-JEPA makes three contributions: (i) CSI-specific tokenization and link masking tailored to the CSI tensor over channel, time, and link (C,T,L); masking entire Tx-Rx antenna links forces the model to predict one spatial link view from others, capturing cross-link correlations informative of 3D spatial structure. (ii) A ray-tracing CSI simulation pipeline that generates diverse unlabeled CSI from randomized geometric primitives, providing scalable pre-training data without pose annotations. (iii) State-of-the-art results on Person-in-WiFi-3D: WiFi-JEPA outperforms prior WiFi-CSI baselines on both single- and multi-person 3D pose estimation under the same evaluation protocol. We also show that simulated CSI provides complementary pre-training signal to real CSI, and that four vision-native SSL objectives degrade performance below training from scratch, whereas WiFi-JEPA consistently improves downstream pose estimation.

Related papers

• Fast Cross-Scenario Adaptation of CSI Models via Channel Conditional Parameter Generation [71.49439535846827]
  Conditional Channel Generation (CCPG) is an end-to-end pipeline for rapid deployment of CSI models in dynamic wireless environments.<n> CCPG identifies scene-sensitive adaptation bottlenecks through component-freezing experiments and generates only lightweight LoRA weights.<n>Experiments on DeepMIMO and WAIR-D for CSI feedback and channel estimation show that CCPG adapts to new scenarios in about 3 seconds with a single forward pass.
  arXiv  Detail & Related papers  (2026-06-22T13:20:01Z)
• CSI-JEPA: Towards Foundation Representations for Ubiquitous Sensing with Minimal Supervision [6.226207559281459]
  We present CSI-JEPA, a self-supervised predictive representation learning framework for label-efficient, multi-task Wi-Fi sensing.<n> CSI-JEPA learns reusable temporal-spectral representations from unlabeled CSI samples.<n>We evaluate CSI-JEPA on seven real-world Wi-Fi sensing tasks spanning diverse objectives and deployment settings.
  arXiv  Detail & Related papers  (2026-05-13T22:50:31Z)
• 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)
• Generative MIMO Beam Map Construction for Location Recovery and Beam Tracking [67.65578956523403]
  This paper proposes a generative framework to recover location labels directly from sparse channel state information (CSI) measurements.<n>Instead of directly storing raw CSI, we learn a compact low-dimensional radio map embedding and leverage a generative model to reconstruct the high-dimensional CSI.<n> Numerical experiments demonstrate that the proposed model can improve localization accuracy by over 30% and achieve a 20% capacity gain in non-line-of-sight (NLOS) scenarios.
  arXiv  Detail & Related papers  (2025-11-21T07:25:49Z)
• Distributed Gossip-GAN for Low-overhead CSI Feedback Training in FDD mMIMO-OFDM Systems [65.23921727688749]
  We propose a novel gossiping generative adversarial network (Gossip-GAN)-aided CSI feedback training framework.<n>Gossip-GAN enables the CSI feedback training with low-overhead while preserving users' privacy.
  arXiv  Detail & Related papers  (2025-08-31T07:46:16Z)
• Hybrid CNN-LSTM based Indoor Pedestrian Localization with CSI Fingerprint Maps [0.0]
  We present a novel Wi-Fi fingerprinting system that uses Channel State Information (CSI) data for fine-grained pedestrian localization.<n>The proposed system exploits the frequency diversity and spatial diversity of the features extracted from CSI data to generate a CSI Fingerprint Map.<n>We then use this CSI Fingerprint Map representation of CSI data to generate a pedestrian trajectory hypothesis using a hybrid architecture.
  arXiv  Detail & Related papers  (2024-12-18T08:31:34Z)
• CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing [19.12026243010111]
  We propose a unified framework named CSI-BERT2 for CSI prediction and classification tasks.<n>The framework adapts BERT to capture the complex relationships among CSI sequences through a bidirectional self-attention mechanism.<n>Extensive experiments on both real-world collected and simulated datasets demonstrate that CSI-BERT2 achieves state-of-the-art performance across all tasks.
  arXiv  Detail & Related papers  (2024-12-09T06:44:04Z)
• 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)
• WiFi-based Spatiotemporal Human Action Perception [53.41825941088989]
  An end-to-end WiFi signal neural network (SNN) is proposed to enable WiFi-only sensing in both line-of-sight and non-line-of-sight scenarios. Especially, the 3D convolution module is able to explore thetemporal continuity of WiFi signals, and the feature self-attention module can explicitly maintain dominant features.
  arXiv  Detail & Related papers  (2022-06-20T16:03:45Z)
• A Wireless-Vision Dataset for Privacy Preserving Human Activity Recognition [53.41825941088989]
  A new WiFi-based and video-based neural network (WiNN) is proposed to improve the robustness of activity recognition. Our results show that WiVi data set satisfies the primary demand and all three branches in the proposed pipeline keep more than $80%$ of activity recognition accuracy.
  arXiv  Detail & Related papers  (2022-05-24T10:49:11Z)
• Blind Federated Edge Learning [93.29571175702735]
  We study federated edge learning (FEEL), where wireless edge devices, each with its own dataset, learn a global model. We propose an analog over-the-air' aggregation scheme, in which the devices transmit their local updates in an uncoded fashion.
  arXiv  Detail & Related papers  (2020-10-19T16:22:28Z)

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.