SDVRF：面向多模态三维目标检测的稀疏到密集体素区域融合（英文版）

英文标题：SDVRF: Sparse-to-Dense Voxel Region Fusion for Multi-modal 3D Object Detection中文摘要：自动驾驶认知任务利用多模态处理器已成为趋势，该文章提出了 Voxel Region 和 Sparse-to-Dense Voxel Region Fusion，该方法增加了像素图像信息，提取了更丰富的特征，提高了不同基线的性能。英文摘要：In the perception task of autonomous driving, multi-modal methods have becomea trend due to the complementary characteristics of LiDAR point clouds andimage data. However, the performance of previous methods is usually limited bythe sparsity of the point cloud or the noise problem caused by