cs.CVNov 10, 2026

HiPFuse: Real-Time LiDAR Semantic Segmentation for Robotic Perception on Edge Devices

Authors: Haiyang Wu, George Vosselman, Ville Lehtola

Organizations: Haiyang Wu, George Vosselman, and Ville Lehtola are with the Department of Geoinformatics, Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, 7522 NB Enschede, The Netherlands.

Abstract

Real-time robotic perception requires accurate LiDAR semantics under limited resources. Bird's-eye-view (BEV) aggregation is efficient but can mix differently labeled surfaces in columns. We present HiPFuse, a point-BEV fusion framework that exchanges point and height-partitioned BEV features across horizontal scales, combining point-wise detail with 2D spatial context from one LiDAR scan. Fixed height assignments preserve separate vertical aggregation groups, with auxiliary supervision of initial BEV features using targets from the same 3D cells. A dual-scale BEV context module adds broader context from a coarser grid. On SemanticKITTI and MCD, HiPFuse achieves 63.7% and 62.5% mIoU at 14.2 and 22.4 FPS on Jetson AGX Orin, respectively, exceeding the 10 Hz scan rate. Separate training and evaluation show indoor applicability. Replacing only the baseline semantic front end with HiPFuse in fixed robotic systems reduces odometry absolute trajectory error RMSE by 10.6% on average across two outdoor sequences and increases accepted-loop recall by 8.7 percentage points on SemanticKITTI. Qualitative semantic maps show more continuous road labeling. Our code is available at https://github.com/haiyang2022/HiPFuse.

Figures & tables

Explore similar work

CardsList
  1. RAHF-Net: Range-Aware Heterogeneous Fusion for LiDAR-Assisted RGB Semantic Segmentation

    Oct 18, 2026R. D. Lin, Pengcheng Weng, Ge Wang +2Camera-LiDAR FusionMultimodal Semantic Segmentation

  2. Real-Time Structural Detection for Indoor Navigation from 3D LiDAR Using Bird's-Eye-View Images

    Mar 20, 2026Guanliang Li, Pedro Espinosa-Angulo, David Perez-Saura +1Robotic PerceptionObject Detection