RIS-Assisted 3D Spherical Splatting for Object Composition Visualization using Detection Transformers

2025-11-04

AI Summary

To address the limited 3D reconstruction accuracy in RF sensing caused by multipath propagation, this paper proposes a novel RIS-assisted RF sensing paradigm. Specifically, reconfigurable intelligent surfaces (RIS) are employed to actively manipulate the wireless channel and establish a controllable RF imaging environment. We introduce spherical primitives—designed for material-aware representation—to jointly model geometric structure and dielectric properties. Furthermore, we adapt the Detection Transformer architecture for RF signal features for the first time, enabling end-to-end joint estimation of 3D object positions and material attributes. Experimental results demonstrate that the method achieves an overall accuracy of 79.35% for simultaneous shape reconstruction and material classification in simulation. This significantly overcomes the limitations of optical imaging under occlusion and low-illumination conditions, offering a new pathway toward non-line-of-sight and all-weather 3D perception.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance

Abstract

The pursuit of immersive and structurally aware multimedia experiences has intensified interest in sensing modalities that reconstruct objects beyond the limits of visible light. Conventional optical pipelines degrade under occlusion or low illumination, motivating the use of radio-frequency (RF) sensing, whose electromagnetic waves penetrate materials and encode both geometric and compositional information. Yet, uncontrolled multipath propagation restricts reconstruction accuracy. Recent advances in Programmable Wireless Environments (PWEs) mitigate this limitation by enabling software-defined manipulation of propagation through Reconfigurable Intelligent Surfaces (RISs), thereby providing controllable illumination diversity. Building on this capability, this work introduces a PWE-driven RF framework for three-dimensional object reconstruction using material-aware spherical primitives. The proposed approach combines RIS-enabled field synthesis with a Detection Transformer (DETR) that infers spatial and material parameters directly from extracted RF features. Simulation results confirm the framework's ability to approximate object geometries and classify material composition with an overall accuracy of 79.35%, marking an initial step toward programmable and physically grounded RF-based 3D object composition visualization.

Problem

• Reconstructing 3D objects under occlusion and low light using RF sensing
• Mitigating multipath propagation limitations via programmable wireless environments
• Estimating object geometry and material composition from RF features

Innovation

• RIS-enabled field synthesis for controlled RF illumination
• Detection Transformer infers spatial and material parameters
• Material-aware spherical primitives reconstruct 3D object composition