Multi-camera 3D perception has emerged as a prominent research field in autonomous driving, offering a viable and cost-effective alternative to LiDAR-based solutions. However, existing multi-camera algorithms primarily rely on monocular image pre-training, which overlooks the spatial and temporal correlations among different camera views. To address this limitation, we propose a novel multi-camera unified pre-training framework called Occ-BEV, which involves initially reconstructing the 3D scene as the foundational stage and subsequently fine-tuning the model on downstream tasks. Specifically, a 3D decoder is designed for leveraging Bird's Eye View (BEV) features from multi-view images to predict the 3D geometry occupancy to enable the model to capture a more comprehensive understanding of the 3D environment. One significant advantage of Occ-BEV is that it can utilize a vast amount of unlabeled image-LiDAR pairs for pre-training. The proposed multi-camera unified pre-training framework demonstrates promising results in key tasks such as multi-camera 3D object detection and semantic scene completion. When compared to monocular pre-training methods on the nuScenes dataset, Occ-BEV demonstrates a significant improvement of 2.0% in mAP and 2.0% in NDS for 3D object detection, as well as a 0.8% increase in mIOU for semantic scene completion. codes are publicly available at https://github.com/chaytonmin/Occ-BEV.

翻译：暂无翻译