OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction

arXiv:2402.18140v1 Announce Type: new
Abstract: This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the strong baseline BEVFormer and improves its performance through several simple yet effective techniques. Firstly, we employed data augmentation to increase the diversity of the training data and improve the model's generalization ability. Secondly, we used a strong image backbone to extract more informative features from the input data. Thirdly, …

abstract arxiv augmentation autonomous autonomous driving challenge cs.cv cvpr data driving performance prediction report simple solution technical through type