论文标题
Matrixvt：有效的多摄像头到3D感知的BEV转换
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
论文作者
论文摘要
本文提出了一个有效的多摄像头，以供鸟眼视图（BEV）视图转换方法，用于3D感知，称为matrixvt。现有的视图变压器要么遭受变换效率不佳或依赖于设备特定的操作员，从而阻碍了BEV模型的广泛应用。相反，我们的方法仅使用卷积和矩阵乘法（MATMUL）有效地生成BEV特征。具体而言，我们建议将BEV特征描述为图像特征的矩阵和稀疏特征运输矩阵（FTM）。然后引入素数模块，以压缩图像特征的维度并减少FTM的稀疏性。此外，我们提出了环\＆射线分解，以用两个矩阵替换FTM并重新制定管道以进一步减少计算。与现有方法相比，Matrixvt的速度更快，内存足迹较小，同时保持对部署友好。在Nuscenes基准上进行的广泛实验表明，我们的方法高效，但在对象检测和MAP分割任务中以SOTA方法获得结果
This paper proposes an efficient multi-camera to Bird's-Eye-View (BEV) view transformation method for 3D perception, dubbed MatrixVT. Existing view transformers either suffer from poor transformation efficiency or rely on device-specific operators, hindering the broad application of BEV models. In contrast, our method generates BEV features efficiently with only convolutions and matrix multiplications (MatMul). Specifically, we propose describing the BEV feature as the MatMul of image feature and a sparse Feature Transporting Matrix (FTM). A Prime Extraction module is then introduced to compress the dimension of image features and reduce FTM's sparsity. Moreover, we propose the Ring \& Ray Decomposition to replace the FTM with two matrices and reformulate our pipeline to reduce calculation further. Compared to existing methods, MatrixVT enjoys a faster speed and less memory footprint while remaining deploy-friendly. Extensive experiments on the nuScenes benchmark demonstrate that our method is highly efficient but obtains results on par with the SOTA method in object detection and map segmentation tasks
