OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping

TL;DR

OneBEV introduces a novel approach for bird's-eye-view semantic mapping using a single panoramic image, employing a distortion-aware module to handle spatial distortions and achieve state-of-the-art results in autonomous driving scenarios.

Contribution

The paper presents a new BEV mapping method that simplifies the process by using only one panoramic image and a specialized distortion-aware module, along with two new datasets.

Findings

Achieves 51.1% mIoU on nuScenes-360

Achieves 36.1% mIoU on DeepAccident-360

Outperforms existing methods in BEV semantic mapping

Abstract

In the field of autonomous driving, Bird's-Eye-View (BEV) perception has attracted increasing attention in the community since it provides more comprehensive information compared with pinhole front-view images and panoramas. Traditional BEV methods, which rely on multiple narrow-field cameras and complex pose estimations, often face calibration and synchronization issues. To break the wall of the aforementioned challenges, in this work, we introduce OneBEV, a novel BEV semantic mapping approach using merely a single panoramic image as input, simplifying the mapping process and reducing computational complexities. A distortion-aware module termed Mamba View Transformation (MVT) is specifically designed to handle the spatial distortions in panoramas, transforming front-view features into BEV features without leveraging traditional attention mechanisms. Apart from the efficient framework, we contribute two datasets, i.e., nuScenes-360 and DeepAccident-360, tailored for the OneBEV task. Experimental results showcase that OneBEV achieves state-of-the-art performance with 51.1% and 36.1% mIoU on nuScenes-360 and DeepAccident-360, respectively. This work advances BEV semantic mapping in autonomous driving, paving the way for more advanced and reliable autonomous systems.