RIS-Aided Wireless Amodal Sensing for Single-View 3D Reconstruction

TL;DR

This paper introduces a RIS-aided wireless amodal sensing system that enhances shape reconstruction of occluded objects by improving spatial resolution and using generative models, achieving significant error reduction.

Contribution

It proposes a novel RIS-aided sensing scheme with an error prediction model to optimize RIS phase shifts for improved 3D shape reconstruction accuracy.

Findings

Achieves at least 56.73% reduction in reconstruction error.

Leverages large-scale RIS to bypass obstacles and enhance sensing.

Employs a generative learning model for complete shape reconstruction.

Abstract

Amodal sensing is critical for various real-world sensing applications because it can recover the complete shapes of partially occluded objects in complex environments. Among various amodal sensing paradigms, wireless amodal sensing is a potential solution due to its advantages of environmental robustness, privacy preservation, and low cost. However, the sensing data obtained by wireless system is sparse for shape reconstruction because of the low spatial resolution, and this issue is further intensified in complex environments with occlusion. To address this issue, we propose a Reconfigurable Intelligent Surface (RIS)-aided wireless amodal sensing scheme that leverages a large-scale RIS to enhance the spatial resolution and create reflection paths that can bypass the obstacles. A generative learning model is also employed to reconstruct the complete shape based on the sensing data captured from the viewpoint of the RIS. In such a system, it is challenging to optimize the RIS phase shifts because the relationship between RIS phase shifts and amodal sensing accuracy is complex and the closed-form expression is unknown. To tackle this challenge, we develop an error prediction model that learns the mapping from RIS phase shifts to amodal sensing accuracy, and optimizes RIS phase shifts based on this mapping. Experimental results on the benchmark dataset show that our method achieves at least a 56.73% reduction in reconstruction error compared to conventional schemes under the same number of RIS configurations.