PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection

2024-05-05 · Zhaoqi Leng, Pei Sun, Tong He, Dragomir Anguelov, Mingxing Tan

3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars. In this paper, we identify that the common PointNet design introduces an information bottleneck that limits 3D object detection accuracy and scalability. To address this limitation, we propose PVTransformer: a transformer-based point-to-voxel architecture for 3D detection. Our key idea is to replace the PointNet pooling operation with an attention module, leading to a better point-to-voxel aggregation function. Our design respects the permutation invariance of sparse 3D points while being more expressive than the pooling-based PointNet. Experimental results show our PVTransformer achieves much better performance compared to the latest 3D object detectors. On the widely used Waymo Open Dataset, our PVTransformer achieves state-of-the-art 76.5 mAPH L2, outperforming the prior art of SWFormer by +1.7 mAPH L2.

📄 PDF Abstract BibTeX arXiv:2405.02811

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionObjectobject-detection Object Detection

SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds

2022-10-13 · Pei Sun, Mingxing Tan, Weiyue Wang, Chenxi Liu 외

3D object detection in point clouds is a core component for modern robotics and autonomous driving systems. A key challenge in 3D object detection comes from the inherent sparse nature of point occupancy within the 3D sc…

3D Object Detection Autonomous Driving Object object-detection+1

PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer

2023-05-11 · CVPR 2023 1 · Honghui Yang, Wenxiao Wang, Minghao Chen, Binbin Lin 외

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization err…

Autonomous Driving Quantization

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds

2022-03-19 · CVPR 2022 1 · Chenhang He, Ruihuang Li, Shuai Li, Lei Zhang

Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to compute the self-attention on large-scale point cloud data because point cloud is a long sequence and unevenly dist…

3D Object Detection object-detection Object Detection

Voxel Transformer for 3D Object Detection

2021-09-06 · ICCV 2021 10 · Jiageng Mao, Yujing Xue, Minzhe Niu, Haoyue Bai 외

We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in voxel-based 3D detectors cannot efficientl…

3D Object Detection Computational Efficiency Object object-detection+2

Masked Autoencoder for Self-Supervised Pre-training on Lidar Point Clouds

2022-07-01 · Georg Hess, Johan Jaxing, Elias Svensson, David Hagerman 외

Masked autoencoding has become a successful pretraining paradigm for Transformer models for text, images, and, recently, point clouds. Raw automotive datasets are suitable candidates for self-supervised pre-training as t…

3D Object Detection object-detection Object Detection Self-Supervised Learning