Published In

2026 IEEE International Conference on Electro Information Technology (eit)

Document Type

Pre-Print

Publication Date

10-2026

Subjects

LiDAR Beams -- engineering

Abstract

Vertical beam dropout in spinning LiDAR sensors -triggered by hardware aging, dust, snow, fog, or bright reflections - removes entire vertical slices from the point cloud and severely degrades 3D perception in autonomous vehicles. This paper proposes a Graph Attention Network (GAT)-based framework that reconstructs these missing vertical channels using only the current LiDAR frame, with no camera images or temporal information required. Each LiDAR sweep is represented as an unstructured spatial graph: points are nodes and edges connect nearby points while preserving the original beam-index ordering. A multi-layer GAT learns adaptive attention weights over local geometric neighborhoods and directly regresses the missing elevation (z) values at dropout locations. Trained and evaluated on 1,065 raw KITTI sequences with simulated channel dropout, the method achieves an average height RMSE of 11.67 cm, with 87.98% of reconstructed points falling within a 10 cm error threshold. The full model execution time is 14.65 seconds per frame, while the inference-only latency is 0.017 seconds per frame on a single GPU. Reconstruction quality remains stable for different neighborhood sizes k. These results show that a pure graph-attention model operating solely on raw point-cloud geometry can effectively recover dropped vertical beams under realistic sensor degradation.

Rights

© Copyright the author(s) 2026

Description

This is the author’s version of a work that was accepted for publication. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published as: (2026). A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams. In (Editor), 2026 IEEE International Conference on Electro Information Technology (eIT). https://doi.org/10.1109/eit68936.2026.11670375

DOI

10.1109/eIT68936.2026.11670375

Persistent Identifier

https://archives.pdx.edu/ds/psu/45216

Publisher

IEEE

Download

Share

COinS