# DoRF++: Spherical Representation Learning over Doppler Radiance Fields for Robust Wi-Fi Sensing

arXiv: https://arxiv.org/abs/2608.08381 · HTML: https://mlsanity.com/paper/2608.08381/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels](https://mlsanity.com/paper/1910.13051/) (2019)
- [SHARP: Environment and Person Independent Activity Recognition with Commodity IEEE 802.11 Access Points](https://mlsanity.com/paper/2103.09924/) (2021)
- [An Overview on IEEE 802.11bf: WLAN Sensing](https://mlsanity.com/paper/2310.17661/) (2023)
- [A Tutorial-cum-Survey on Self-Supervised Learning for Wi-Fi Sensing: Trends, Challenges, and Outlook](https://mlsanity.com/paper/2506.12052/) (2025)
- [Attention on the Sphere](https://mlsanity.com/paper/2505.11157/) (2025)
- [Joint Human Orientation-Activity Recognition Using WiFi Signals for Human-Machine Interaction](https://mlsanity.com/paper/2210.05078/) (2022)
- [MELON: NeRF with Unposed Images in SO(3)](https://mlsanity.com/paper/2303.08096/) (2023)
- [MORIC: CSI Delay-Doppler Decomposition for Robust Wi-Fi-based Human Activity Recognition](https://mlsanity.com/paper/2506.12997/) (2025)
- [DoRF: Doppler Radiance Fields for Robust Human Activity Recognition Using Wi-Fi](https://mlsanity.com/paper/2507.12132/) (2025)
- [Doppler Radiance Field-Guided Antenna Selection for Improved Generalization in Multi-Antenna Wi-Fi-based Human Activity Recognition](https://mlsanity.com/paper/2509.15129/) (2025)
- [Beyond Amplitude: Channel State Information Phase-Aware Deep Fusion for Robotic Activity Recognition](https://mlsanity.com/paper/2603.09047/) (2026)

## Abstract (arXiv)

Motivated by the IEEE 802.11bf effort to standardize advanced WLAN sensing, interest in Wi-Fi Channel State Information (CSI) for passive, device-free, and privacy-preserving activity and gesture recognition has grown rapidly. Recent studies have shown that Doppler velocity projections extracted from CSI, which directly reflect human-motion velocity, enable more robust human activity recognition (HAR) and stronger generalization across users and unseen conditions. Nevertheless, reliable generalization under real-world variability remains a major challenge that hinders the adoption of Wi-Fi sensing. To address this challenge, we build on Doppler Radiance Fields (DoRF), adapting the concept of neural radiance fields (NeRF) from computer vision to Wi-Fi sensing. DoRF treats the extracted Doppler velocity projections as sparse virtual-camera views of human motion. From these views it recovers a regularized latent 3-D motion descriptor whose projections along learned effective Doppler directions explain the CSI observations. The recovered motion is then re-projected onto an equiangular grid of directions on the unit sphere, yielding a spherical representation of the underlying activity. Because DoRF produces a signal defined on the sphere, this paper introduces DoRF++, a spherical representation-learning model that applies quadrature-aware spherical Transformers directly to the spherical field for activity classification. Experiments on our collected hand-gesture dataset show that DoRF++ noticeably outperforms state-of-the-art Wi-Fi-based HAR methods in cross-user generalization accuracy, especially for difficult gestures when only a single multi-antenna receiver access point (AP) is available.