Re-VoxelDet: Rethinking Neck and Head Architectures for High-Performance Voxel-based 3D Detection

초록

LiDAR-based 3D object detectors usually adopt grid-based approaches to handle sparse point clouds efficiently. However, during this process, the down-sampled features inevitably lose spatial information, which can hinder the detectors from accurately predicting the location and size of objects. To address this issue, previous researches proposed sophisticatedly designed neck and head modules to effectively compensate for information loss. Inspired by the core insights of previous studies, we propose a novel voxel-based 3D object detector, named as Re-VoxelDet, which combines three distinct components to achieve both good detection capability and real-time performance. First, in order to learn features from diverse perspectives without additional computational costs during inference, we introduce Multi-view Voxel Backbone (MVBackbone). Second, to effectively compensate for abundant spatial and strong semantic information, we design Hierarchical Voxel-guided Auxiliary Neck (HVANeck), which attentively integrates hierarchically generated voxel-wise features with RPN blocks. Third, we present Rotation-based Group Head (RGHead), a simple yet effective head module that is designed with two groups according to the heading direction and aspect ratio of the objects. Through extensive experiments on the Argoverse2, Waymo Open Dataset and nuScenes, we demonstrate the effectiveness of our approach. Our results significantly outperform existing state-of-the-art methods. We plan to release our model and code(1) in the near future.

키워드