Diffusion^2: Turning 3D Environments into Radio Freqneucny Heatmaps

ICLR 2026 Conference Submission13097 Authors

Keywords: Wireless Networks, Diffusion

TL;DR: Diffusion^2 turns 3D environments into RF heatmaps and videos with high accuracy and up to 27x faster inference than prior methods, using only minimal measurements.

Abstract: Modeling radio frequency (RF) signal propagation is essential for understanding the environment as RF signals offer valuable insights beyond the capabilities of RGB cameras, which are limited by the visible light spectrum, lens coverage, and occlusions. It is also useful for supporting wireless diagnosis, deployment, and optimization. However, accurately predicting RF signals in complex environments remains challenging because of interactions with obstacles such as absorption and reflection. We introduce Diffusion^2, a diffusion-based approach that leverages 3D point clouds to model the propagation of RF signals across a wide range of frequencies, from Wi-Fi to millimeter waves. To effectively capture RF-related features from 3D data, we present the RF-3D Encoder, which encapsulates the complexities of 3D geometry along with signal-specific details. These features undergo multi-scale embedding to simulate the actual RF signal dissemination process. Our evaluation, based on synthetic and real-world measurements, demonstrates that Diffusion^2 accurately estimates the behavior of RF signals in various frequency bands and environmental conditions, with an error margin of just 1.9 dB and 27x faster than the existing methods, marking a significant advancement in the field. Refer to https://rfvision-project.github.io/ for more information.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 13097