RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes

TL;DR

RF4D introduces a radar-based neural field framework that leverages millimeter-wave radar data and temporal modeling to enable robust, accurate, and temporally consistent novel view synthesis in outdoor dynamic scenes, especially under adverse weather conditions.

Contribution

RF4D is the first neural field approach integrating radar data with explicit temporal modeling and scene flow for outdoor dynamic scene synthesis, enhancing robustness and accuracy.

Findings

Outperforms existing methods in radar measurement synthesis.

Achieves higher occupancy estimation accuracy.

Demonstrates strong results in dynamic outdoor environments.

Abstract

Neural fields (NFs) have achieved remarkable success in scene reconstruction and novel view synthesis. However, existing NF approaches that rely on RGB or LiDAR inputs often struggle under adverse weather conditions, limiting their robustness in real-world outdoor environments such as autonomous driving. In contrast, millimeter-wave radar is inherently resilient to environmental variations, yet its integration with NFs remains largely underexplored. Moreover, outdoor driving scenes frequently involve dynamic objects, making spatiotemporal modeling crucial for temporally consistent novel view synthesis. To address these challenges, we present RF4D, a radar-based neural field framework tailored for novel view synthesis in outdoor dynamic scenes. RF4D explicitly incorporates temporal information into its representation, enabling more accurate modeling of object motion. A dedicated scene flow module further predicts temporal offsets between adjacent frames, enforcing temporal occupancy coherence during dynamic scene reconstruction. Moreover, we propose a radar-specific power rendering formulation grounded in radar sensing physics, improving both synthesis accuracy and interpretability. Extensive experiments on public radar datasets demonstrate that RF4D substantially outperforms existing methods in radar measurement synthesis and occupancy estimation accuracy, with particularly strong gains in dynamic outdoor environments.