REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion

TL;DR

REXO introduces a novel 3D bounding box diffusion approach for multi-view indoor radar object detection, explicitly associating cross-view features and significantly improving detection accuracy over existing methods.

Contribution

The paper proposes REXO, a new method that lifts 2D bounding box diffusion into 3D radar space for explicit cross-view feature association, reducing ambiguity and enhancing detection performance.

Findings

Surpasses state-of-the-art by +4.22 AP on HIBER dataset.

Achieves +11.02 AP improvement on MMVR dataset.

Effectively reduces diffusion parameters by leveraging ground contact prior.

Abstract

Multi-view indoor radar perception has drawn attention due to its cost-effectiveness and low privacy risks. Existing methods often rely on {implicit} cross-view radar feature association, such as proposal pairing in RFMask or query-to-feature cross-attention in RETR, which can lead to ambiguous feature matches and degraded detection in complex indoor scenes. To address these limitations, we propose \textbf{REXO} (multi-view Radar object dEtection with 3D bounding boX diffusiOn), which lifts the 2D bounding box (BBox) diffusion process of DiffusionDet into the 3D radar space. REXO utilizes these noisy 3D BBoxes to guide an {explicit} cross-view radar feature association, enhancing the cross-view radar-conditioned denoising process. By accounting for prior knowledge that the person is in contact with the ground, REXO reduces the number of diffusion parameters by determining them from this prior. Evaluated on two open indoor radar datasets, our approach surpasses state-of-the-art methods by a margin of +4.22 AP on the HIBER dataset and +11.02 AP on the MMVR dataset. The REXO implementation is available at https://github.com/merlresearch/radar-bbox-diffusion.