ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9466-9475
Abstract
Problems such as equipment defects or limited view-points will lead the captured point clouds to be incomplete. Therefore, recovering the complete point clouds from the partial ones plays an vital role in many practical tasks, and one of the keys lies in the prediction of the missing part. In this paper, we propose a novel point cloud completion approach namely ProxyFormer that divides point clouds into existing (input) and missing (to be predicted) parts and each part communicates information through its proxies. Specifically, we fuse information into point proxy via feature and position extractor, and generate features for missing point proxies from the features of existing point proxies. Then, in order to better perceive the position of missing points, we design a missing part sensitive transformer, which converts random normal distribution into reasonable position information, and uses proxy alignment to refine the missing proxies. It makes the predicted point proxies more sensitive to the features and positions of the missing part, and thus makes these proxies more suitable for subsequent coarse-to-fine processes. Experimental results show that our method outperforms state-of-the-art completion networks on several benchmark datasets and has the fastest inference speed.Keywords
Funding Information
- National Key Research and Development Program of China (2021ZD0113203)
- Natural Science Foundation of China (62272227)
This publication has 38 references indexed in Scilit:
- PCN: Point Completion Network2018
- FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation2018
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- Database‐Assisted Object Retrieval for Real‐Time 3D ReconstructionComputer Graphics Forum, 2015
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Learning part-based templates from large collections of 3D shapesACM Transactions on Graphics, 2013
- Symmetry in 3D Geometry: Extraction and ApplicationsComputer Graphics Forum, 2013
- A search-classify approach for cluttered indoor scene understandingACM Transactions on Graphics, 2012
- Discovering structural regularity in 3D geometry2008
- A robust hole-filling algorithm for triangular meshThe Visual Computer, 2007