SEFormer: Structure Embedding Transformer for 3D Object Detection
This work addresses a key problem in autonomous driving by improving 3D object detection accuracy on sparse LiDAR data, though it is incremental as it builds upon existing Transformer methods.
The paper tackles the challenge of preserving and encoding structure features in irregular LiDAR point clouds for 3D object detection by proposing SEFormer, a Structure-Embedding Transformer that learns feature transformations based on relative directions and distances. It achieves state-of-the-art results with 79.02% mAP on the Waymo Open Dataset, a 1.2% improvement over existing methods.
Effectively preserving and encoding structure features from objects in irregular and sparse LiDAR points is a key challenge to 3D object detection on point cloud. Recently, Transformer has demonstrated promising performance on many 2D and even 3D vision tasks. Compared with the fixed and rigid convolution kernels, the self-attention mechanism in Transformer can adaptively exclude the unrelated or noisy points and thus suitable for preserving the local spatial structure in irregular LiDAR point cloud. However, Transformer only performs a simple sum on the point features, based on the self-attention mechanism, and all the points share the same transformation for value. Such isotropic operation lacks the ability to capture the direction-distance-oriented local structure which is important for 3D object detection. In this work, we propose a Structure-Embedding transFormer (SEFormer), which can not only preserve local structure as traditional Transformer but also have the ability to encode the local structure. Compared to the self-attention mechanism in traditional Transformer, SEFormer learns different feature transformations for value points based on the relative directions and distances to the query point. Then we propose a SEFormer based network for high-performance 3D object detection. Extensive experiments show that the proposed architecture can achieve SOTA results on Waymo Open Dataset, the largest 3D detection benchmark for autonomous driving. Specifically, SEFormer achieves 79.02% mAP, which is 1.2% higher than existing works. We will release the codes.