X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation

TL;DR

X-Align introduces a novel framework that improves bird's-eye-view segmentation in autonomous driving by better aligning multi-modal and multi-view features, significantly outperforming previous methods.

Contribution

It proposes a new end-to-end cross-modal and cross-view learning framework with novel alignment losses and modules for improved BEV segmentation.

Findings

Outperforms state-of-the-art by 3 mIoU on nuScenes

Effective multi-modal feature fusion via attention-based module

Enhanced PV-to-BEV transformation accuracy

Abstract

Bird's-eye-view (BEV) grid is a common representation for the perception of road components, e.g., drivable area, in autonomous driving. Most existing approaches rely on cameras only to perform segmentation in BEV space, which is fundamentally constrained by the absence of reliable depth information. Latest works leverage both camera and LiDAR modalities, but sub-optimally fuse their features using simple, concatenation-based mechanisms. In this paper, we address these problems by enhancing the alignment of the unimodal features in order to aid feature fusion, as well as enhancing the alignment between the cameras' perspective view (PV) and BEV representations. We propose X-Align, a novel end-to-end cross-modal and cross-view learning framework for BEV segmentation consisting of the following components: (i) a novel Cross-Modal Feature Alignment (X-FA) loss, (ii) an attention-based Cross-Modal Feature Fusion (X-FF) module to align multi-modal BEV features implicitly, and (iii) an auxiliary PV segmentation branch with Cross-View Segmentation Alignment (X-SA) losses to improve the PV-to-BEV transformation. We evaluate our proposed method across two commonly used benchmark datasets, i.e., nuScenes and KITTI-360. Notably, X-Align significantly outperforms the state-of-the-art by 3 absolute mIoU points on nuScenes. We also provide extensive ablation studies to demonstrate the effectiveness of the individual components.