DiFF: Doppler-informed Flow Matching for Human Motion Flow

arXiv:2609.39098v1 Announce Type: cross Abstract: Perceiving human motion via privacy-preserving 4D millimeter-wave (mmWave) radar is critical for next-generation human-robot interaction (HRI), where point cloud scene flow serves as a foundational motion representation. Yet the extreme sparsity and noise of 4D radar point clouds make non-rigid motion flow estimation severely ill-posed--a challenge that existing rigid-centric methods and prior works fail to adequately address, largely because they neglect the rich Doppler velocity cues inherent in 4D radar. We propose DiFF, a generative framework that marries Doppler-informed motion priors with a Kolmogorov-Arnold Network (KAN)-based conditional flow matching model. At its core, a KAN-attention mechanism enables expressive feature extraction, while a prior-guided generative process harnesses Doppler cues to regularize the ill-posed solution space. Extensive experiments show that DiFF achieves state-of-the-art (SOTA) performance across diverse real-world datasets, reducing 3D endpoint error to the millimeter scale on the mmBody benchmark.

Related

• Privacy-Preserving Full-Body Meshing from mmWave Radar via Mesh Foundation Model Supervision
• RadProPoser: Probabilistic Radar Tensor Human Pose Estimation That Knows Its Limits
• Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies
• Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
• Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction

Source: arXiv cs.CV | 2026-10-01