mmDiffusion: mmWave Diffusion for Sequential 3D Human Dense Point Cloud Generation

Qian Xie, Xinyu Hou, Qianyi Deng, Amir Patel, Niki Trigoni, Andrew Markham

Keywords: mmWave, point cloud, 3D human, diffuion

Abstract: Owing to the distinctive attributes inherent to mmWave radar, the utilization of millimeter-wave (mmWave) point cloud data in contexts involving human-related scenarios is poised to yield significant promise. However, the generation of dense and temporally consistent 3D human point clouds from sequential mmWave signals is a challenging task, yet a critical endeavor with far-reaching implications. In this work, we present a groundbreaking approach to address the challenge of generating dense and temporally consistent 3D human point clouds from sequential mmWave signals. We redefine the problem as a 3D point cloud denoising task, leveraging reverse diffusion processes to transform sparse mmWave data into detailed human representations. Our proposed method, mmDiffusion, effectively exploits diffusion models and temporal context within mmWave sequences to learn the denoising process, resulting in denser and temporally coherent human point clouds. We also introduce a novel evaluation metric tailored to measure temporal consistency. Experimental results demonstrate that mmDiffusion outperforms existing methods. Code and dataset will be public upon acceptance.

Submission Number: 110