OccFusion: A Straightforward and Effective Multi-Sensor Fusion Framework for 3D Occupancy Prediction

Author:

Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Stewart Worrall

Keyword:

Computer Science, Computer Vision and Pattern Recognition, Computer Vision and Pattern Recognition (cs.CV), Robotics (cs.RO)

journal:

date:

2024-03-03 00:00:00

Abstract

This paper introduces OccFusion, a straightforward and efficient sensor fusion framework for predicting 3D occupancy. A comprehensive understanding of 3D scenes is crucial in autonomous driving, and recent models for 3D semantic occupancy prediction have successfully addressed the challenge of describing real-world objects with varied shapes and classes. However, existing methods for 3D occupancy prediction heavily rely on surround-view camera images, making them susceptible to changes in lighting and weather conditions. By integrating features from additional sensors, such as lidar and surround view radars, our framework enhances the accuracy and robustness of occupancy prediction, resulting in top-tier performance on the nuScenes benchmark. Furthermore, extensive experiments conducted on the nuScenes dataset, including challenging night and rainy scenarios, confirm the superior performance of our sensor fusion strategy across various perception ranges. The code for this framework will be made available at https://github.com/DanielMing123/OCCFusion.

PDF: OccFusion: A Straightforward and Effective Multi-Sensor Fusion Framework for 3D Occupancy Prediction.pdf