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

2025-11-21

AI Summary

To address the matching ambiguity and degraded detection performance caused by implicit cross-view feature association in multi-view indoor radar perception, this paper proposes REXO—a novel framework that explicitly models inter-view correspondences. REXO pioneers the extension of 2D bounding-box diffusion to 3D radar space, establishing an explicit cross-view feature association mechanism. It incorporates a ground-contact physical prior to constrain the parameter learning of the diffusion process, thereby reducing model complexity and enhancing robustness. Furthermore, REXO integrates denoising-based training with radar-specific feature alignment to achieve high-precision 3D object detection. Evaluated on the HIBER and MMVR benchmarks, REXO achieves absolute AP improvements of 4.22 and 11.02, respectively, significantly surpassing existing state-of-the-art methods.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Diffusion Models for Vision
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

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 extbf{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.

Problem

• Addresses ambiguous feature matches in multi-view indoor radar detection
• Enhances cross-view radar feature association using 3D bounding box diffusion
• Improves detection accuracy in complex indoor scenes with prior knowledge

Innovation

• 3D bounding box diffusion for radar detection
• Explicit cross-view radar feature association
• Reduced diffusion parameters using ground contact prior