VFR-Net: Varifocal Fine-Grained Refinement Network for 3D Object Detection

High-precision 3D object detection is pivotal for autonomous driving. However, voxel-based two-stage detectors still struggle with small and non-rigid objects due to the misalignment between classification confidence and localization accuracy, and the loss of fine-grained spatial context during feature flattening. To address these issues, we propose the Varifocal Fine-grained Refinement Network (VFR-Net). We introduce Varifocal Loss (VFL) to learn IoU-aware scores for prioritizing high-quality proposals, and a Fine-Grained Refinement Attention (FGRA) Module to capture local geometric details via self-attention before flattening. Extensive experiments on the KITTI and ONCE datasets demonstrate that VFR-Net consistently outperforms the Voxel R-CNN baseline, improving the overall mAP by +1.12% on KITTI and +2.63% on ONCE. Specifically, it achieves AP gains of +1.81% and +1.28% for pedestrians and cyclists on KITTI (averaged over Easy/Moderate/Hard), and +6.53% and +1.50% on ONCE (Overall).