Resolving Mixed Single-Photon LiDAR Returns for Foreground-View and Hidden Scene Reconstruction

2026-10-01

AI Summary

This study addresses the challenge of echo aliasing in single-photon LiDAR caused by translucent occlusions, which impedes the separation of foreground and hidden scene geometries. To overcome this, we propose a state-aware neural field framework that incorporates an echo state inference mechanism to distinguish single from dual echoes. By routing supervision signals via local evidence, this approach drives a dual-head neural field to jointly reconstruct foreground views and the 3D structure of hidden scenes. Key contributions include constructing the first real-world paired single-photon LiDAR occlusion dataset and transcending the limitations of conventional single-surface fitting. Experiments demonstrate that our method significantly improves depth estimation accuracy and point cloud quality for hidden scenes on real-world data, validating the feasibility of 3D perception through translucent media.

Abstract

Partially transmissive screens and protective covers are common in robotic inspection, but they create mixed LiDAR returns from both the foreground material and the scene behind it. Conventional peak-based LiDAR usually discards weak hidden returns, while single-photon LiDAR records time-resolved histograms that preserve attenuated and overlapping echoes. However, existing transient reconstruction methods typically fit a single scene representation to the measured waveform. Under occlusion, weak or nearby foreground--hidden echoes can form a broad peak or subtle shoulder. Because such waveforms can also be explained by a displaced single surface or a thick density distribution, accurate transient fitting does not necessarily imply correct geometry. We propose a state-aware framework for foreground-view and hidden scene reconstruction from occluded single-photon histograms. For each ray, we estimate local echo evidence, identifying no reliable surface evidence, single-return evidence, or two returns. The inferred echo state routes supervision for a two-head neural field: all rays constrain waveform reconstruction, while reliable anchors provide geometry localization. We also introduce a real paired single-photon LiDAR occlusion dataset with occluded and clean captures at fixed poses. Experiments on a real dataset show improved hidden scene depth and point-cloud accuracy over baselines. Our results demonstrate single-photon layered reconstruction as a practical route for 3D perception through partially transmissive occluders.

Problem

• Single-Photon LiDAR
• Occlusion
• Mixed Returns
• Hidden Scene Reconstruction
• Transient Imaging

Innovation

• Single-Photon LiDAR
• State-Aware Framework
• Neural Fields
• Occlusion Reconstruction
• Transient Imaging