PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection

Yidi Li, Jiahao Wen, Rui Gong, Bin Ren, Wenhao Li, Chen Cheng, Hong Liu, Nicu Sebe

Abstract: Highlights•PVAFN: A novel network for 3D object detection, fusing keypoint, voxel, and BEV features dynamically.•Stage-I: Dual-gated hierarchical attention fusion for bidirectional point-voxel feature calibration.•Stage-II: Density-spatial-aware multi-pooling module enhances local and global geometric perception.•SOTA Performance: PVAFN achieves highest AP on KITTI and Waymo benchmarks for autonomous driving.