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

TL;DR

This work addresses RF-based 3D object reconstruction under multipath by leveraging programmable wireless environments (PWEs) and RISs to control illumination. It introduces a material-aware 3D spherical splatting approach, where objects are represented as assemblies of spherical primitives and RF features are extracted under diverse RIS configurations. A Detection Transformer (DETR) maps RF features to the parameters of these primitives and their material labels, trained with bipartite assignment and a combination of $\ell_1$ and 3D GIoU losses; performance is demonstrated via ray-tracing simulations, achieving sub-meter localization and $p=0.7935$ material-accuracy. The framework provides a physically grounded, data-driven pathway for RF-based volumetric object visualization in PWEs, with practical implications for robust sensing under occlusion and low illumination.

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.

Figures (4)

• Figure 1: Overview of the 3D-object reconstruction system.
• Figure 2: Boxplots of Absolute Mean Errors Across all Spherical Primitives.
• Figure 3: Confusion matrix for the material classification task.
• Figure 4: Qualitative results across $4$ arbitrary object geometries.