SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cao, Helin, Materla, Rafael, Behnke, Sven
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908487419691008
author Cao, Helin
Materla, Rafael
Behnke, Sven
author_facet Cao, Helin
Materla, Rafael
Behnke, Sven
contents Perception systems in autonomous driving rely on sensors such as LiDAR and cameras to perceive the 3D environment. However, due to occlusions and data sparsity, these sensors often fail to capture complete information. Semantic Occupancy Prediction (SOP) addresses this challenge by inferring both occupancy and semantics of unobserved regions. Existing transformer-based SOP methods lack explicit modeling of spatial structure in attention computation, resulting in limited geometric awareness and poor performance in sparse or occluded areas. To this end, we propose Spatially-aware Window Attention (SWA), a novel mechanism that incorporates local spatial context into attention. SWA significantly improves scene completion and achieves state-of-the-art results on LiDAR-based SOP benchmarks. We further validate its generality by integrating SWA into a camera-based SOP pipeline, where it also yields consistent gains across modalities.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18785
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving
Cao, Helin
Materla, Rafael
Behnke, Sven
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
Perception systems in autonomous driving rely on sensors such as LiDAR and cameras to perceive the 3D environment. However, due to occlusions and data sparsity, these sensors often fail to capture complete information. Semantic Occupancy Prediction (SOP) addresses this challenge by inferring both occupancy and semantics of unobserved regions. Existing transformer-based SOP methods lack explicit modeling of spatial structure in attention computation, resulting in limited geometric awareness and poor performance in sparse or occluded areas. To this end, we propose Spatially-aware Window Attention (SWA), a novel mechanism that incorporates local spatial context into attention. SWA significantly improves scene completion and achieves state-of-the-art results on LiDAR-based SOP benchmarks. We further validate its generality by integrating SWA into a camera-based SOP pipeline, where it also yields consistent gains across modalities.
title SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2506.18785