FB-BEV: BEV Representation from Forward-Backward View Transformations

2023 IEEE/CVF International Conference on Computer Vision (ICCV)(2023)

引用 23|浏览210
暂无评分
摘要
View Transformation Module (VTM), where transformations happen between multi-view image features and Bird-Eye-View (BEV) representation, is a crucial step in camera-based BEV perception systems. Currently, the two most prominent VTM paradigms are forward projection and backward projection. Forward projection, represented by Lift-Splat-Shoot, leads to sparsely projected BEV features without post-processing. Backward projection, with BEVFormer being an example, tends to generate false-positive BEV features from incorrect projections due to the lack of utilization on depth. To address the above limitations, we propose a novel forward-backward view transformation module. Our approach compensates for the deficiencies in both existing methods, allowing them to enhance each other to obtain higher quality BEV representations mutually. We instantiate the proposed module with FB-BEV, which achieves a new state-of-the-art result of 62.4\% NDS on the nuScenes test set. The code will be released at \url{https://github.com/NVlabs/FB-BEV}.
更多
查看译文
关键词
fb-bev representation,view,forward-backward
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要