# TriBand-BEV: Real-Time LiDAR-Only 3D Pedestrian Detection via Height-Aware BEV and High-Resolution Feature Fusion

Source: [TriBand-BEV: Real-Time LiDAR-Only 3D Pedestrian Detection via Height-Aware BEV and High-Resolution Feature Fusion](<https://www.sota2.com/research/paper/6a0405dddbc836b87d8278ac>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-18T05:00:14.654Z

Authors: Mohammad Khoshkdahan, Alexey Vinel

Published: 2026-05-12T14:58:16.000Z

## Abstract

Safe autonomous agents and mobile robots need fast real time 3D perception, especially for vulnerable road users (VRUs) such as pedestrians. We introduce a new bird's eye view (BEV) encoding, which maps the full 3D LiDAR point cloud into a light-weight 2D BEV tensor with three height bands. We explicitly reformulate 3D detection as a 2D detection problem and then reconstruct 3D boxes from the BEV outputs. A single network detects cars, pedestrians, and cyclists in one pass. The backbone uses area attention at deep stages, a hierarchical bidirectional neck over P1 to P4 fuses context and detail, and the head predicts oriented boxes with distribution focal learning for side offsets and a rotated IoU loss. Training applies a small vertical re bin and a mild reflectance jitter in channel space to resist memorization. We use an interquartile range (IQR) filter to remove noisy and outlier LiDAR points during 3D reconstruction. On KITTI dataset, TriBand-BEV attains 58.7/52.6/47.2 pedestrian BEV AP(%) for easy, moderate, and hard at 49 FPS on a single consumer GPU, surpassing Complex-YOLO, with gains of +12.6%, +7.5%, and +3.1%. Qualitative scenes show stable detection under occlusion. The pipeline is compact and ready for real time robotic deployment. Our source code is publicly available on GitHub.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Pedestrian 3D Object Detection on KITTI (val)](<https://www.sota2.com/research/sota/pedestrian-3d-object-detection-on-kitti-val.md>): Pedestrian 3D Object Detection; KITTI (val); AP BEV (Easy): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.12220>)

[PDF](<https://arxiv.org/pdf/2605.12220.pdf>)