KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: E, Wenke, Sun, Yixin, Liu, Jiaxu, Shum, Hubert P. H., Atapour-Abarghouei, Amir, Breckon, Toby P.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915681742618624
author E, Wenke
Sun, Yixin
Liu, Jiaxu
Shum, Hubert P. H.
Atapour-Abarghouei, Amir
Breckon, Toby P.
author_facet E, Wenke
Sun, Yixin
Liu, Jiaxu
Shum, Hubert P. H.
Atapour-Abarghouei, Amir
Breckon, Toby P.
contents We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird's-Eye-View (BEV) segmentation. Our approach leverages a novel LiDAR image representation fused from range, intensity and ambient channels, together with a voxel-aligned view transformer that preserves spatial fidelity while enabling efficient BEV processing. During training, a high-capacity LiDAR and camera fusion Teacher network extracts both rich spatial and semantic features for cross-modality knowledge distillation into a lightweight Student network that relies solely on a single 360-degree panoramic camera image. Extensive experiments on the Dur360BEV dataset demonstrate that our teacher model significantly outperforms existing camera-based BEV segmentation methods, achieving a 25.6\% IoU improvement. Meanwhile, the distilled Student network attains competitive performance with an 8.5\% IoU gain and state-of-the-art inference speed of 31.2 FPS. Moreover, evaluations on KITTI-360 (two fisheye cameras) confirm that our distillation framework generalises to diverse camera setups, underscoring its feasibility and robustness. This approach reduces sensor complexity and deployment costs while providing a practical solution for efficient, low-cost BEV segmentation in real-world autonomous driving.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15311
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation
E, Wenke
Sun, Yixin
Liu, Jiaxu
Shum, Hubert P. H.
Atapour-Abarghouei, Amir
Breckon, Toby P.
Computer Vision and Pattern Recognition
We present the first cross-modality distillation framework specifically tailored for single-panoramic-camera Bird's-Eye-View (BEV) segmentation. Our approach leverages a novel LiDAR image representation fused from range, intensity and ambient channels, together with a voxel-aligned view transformer that preserves spatial fidelity while enabling efficient BEV processing. During training, a high-capacity LiDAR and camera fusion Teacher network extracts both rich spatial and semantic features for cross-modality knowledge distillation into a lightweight Student network that relies solely on a single 360-degree panoramic camera image. Extensive experiments on the Dur360BEV dataset demonstrate that our teacher model significantly outperforms existing camera-based BEV segmentation methods, achieving a 25.6\% IoU improvement. Meanwhile, the distilled Student network attains competitive performance with an 8.5\% IoU gain and state-of-the-art inference speed of 31.2 FPS. Moreover, evaluations on KITTI-360 (two fisheye cameras) confirm that our distillation framework generalises to diverse camera setups, underscoring its feasibility and robustness. This approach reduces sensor complexity and deployment costs while providing a practical solution for efficient, low-cost BEV segmentation in real-world autonomous driving.
title KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.15311