6-D Object Pose Estimation Using Multiscale Point Cloud Transformer
- 23 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-11
Abstract
Predicting 6D object pose is an essential task in vision measurement for robotic manipulation. RGB-based methods have a natural disadvantage due to the lack of 3D information, thus leading to inferior results. Therefore, exploiting the geometry information in depth images is crucial to achieve accurate predictions. To this end, we propose a multi-scale point cloud Transformer (MSPCT) to better learn point cloud feature representations. MSPCT mainly consists of three types of modules: Local Transformer (LT), DownSampling module and Global Transformer (GT). Specifically, the Local Transformer is designed to dynamically divide a local region centered on each point and further extract point-level feature with local context awareness. The DownSampling module is utilized to decrease the resolution and enlarge the receptive field. Global Transformer is employed to capture global-range dependencies between extracted local features. Based on the proposed Transformer blocks, we design a network architecture for object pose estimation, where we further obtain multi-scale features by fusing the local features from LT and global features from GT to predict object’s pose. Extensive experiments verify the effectiveness of Local Transformer and Global Transformer, and our pose estimation pipeline achieves promising results on three benchmark datasets.Keywords
Funding Information
- National Natural Science Foundation of China (61733013, 62073245, 62173248)
- Suzhou Science and Technology Development Plan Project (SGC2021035)
- Special funds for Jiangsu Science and Technology Plan (BE2022119)
This publication has 44 references indexed in Scilit:
- PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes2018
- BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth2017
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2017
- Semantic Scene Completion from a Single Depth Image2017
- Deep Residual Learning for Image Recognition2016
- Uncertainty-Driven 6D Pose Estimation of Objects and Scenes from a Single RGB Image2016
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- The YCB object and Model set: Towards common benchmarks for manipulation research2015
- EPnP: An Accurate O(n) Solution to the PnP ProblemInternational Journal of Computer Vision, 2008
- Iterative point matching for registration of free-form curves and surfacesInternational Journal of Computer Vision, 1994