# RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes Source: [RF4D:Neural Radar Fields for Novel View Synthesis in Outdoor Dynamic Scenes]() Collection index: [llms.txt]() Data updated: 2026-03-14T05:00:03.952Z Authors: Jiarui Zhang, Zhihao Li, Chong Wang, Bihan Wen Published: 2025-05-27T09:59:05.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Radar Novel View Synthesis on RobotCar (Scene 1)](): Radar Novel View Synthesis; RobotCar (Scene 1); SSIM: 0.6103. - [Radar Novel View Synthesis on RobotCar (Scene 2)](): Radar Novel View Synthesis; RobotCar (Scene 2); SSIM: 53.5. - [Radar Novel View Synthesis on RobotCar (Scene 3)](): Radar Novel View Synthesis; RobotCar (Scene 3); SSIM: 62.58. - [Radar Novel View Synthesis on RobotCar (Scene 4)](): Radar Novel View Synthesis; RobotCar (Scene 4); SSIM: 49.71. - [Radar Novel View Synthesis on Boreas Sun scenario](): Radar Novel View Synthesis; Boreas Sun scenario; SSIM: 70.01. - [Radar Novel View Synthesis on Boreas Snow scenario](): Radar Novel View Synthesis; Boreas Snow scenario; SSIM: 79.46. - [Radar Novel View Synthesis on Boreas Rain scenario](): Radar Novel View Synthesis; Boreas Rain scenario; SSIM: 66.35. - [Radar Novel View Synthesis on Boreas Static scenario](): Radar Novel View Synthesis; Boreas Static scenario; SSIM: 77.24. - [Occupancy Estimation on Oxford RobotCar Scene 1](): Occupancy Estimation; Oxford RobotCar Scene 1; CD: 7.3449. - [Occupancy Estimation on Oxford RobotCar Scene 2](): Occupancy Estimation; Oxford RobotCar Scene 2; CD: 8.0909. - [Occupancy Estimation on Oxford RobotCar Scene 3](): Occupancy Estimation; Oxford RobotCar Scene 3; CD: 3.2896. - [Occupancy Estimation on Boreas Sun](): Occupancy Estimation; Boreas Sun; CD: 5.4482. - [Occupancy Estimation on Boreas Static](): Occupancy Estimation; Boreas Static; CD: 8.0739. - [Occupancy Estimation on Oxford RobotCar Scene 4](): Occupancy Estimation; Oxford RobotCar Scene 4; CD: 18.7607. - [Occupancy Estimation on Boreas Rain](): Occupancy Estimation; Boreas Rain; CD: 10.4558. ## Original sources and implementation [Original paper]() [PDF]()