.png){kind=icon}
返回
Adaptive Recurrent Forward Network for Dense Point Cloud Completion
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2022.3200851.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Point cloud completion is an interesting and challenging task in 3D vision, which aims to recover complete shapes from sparse and incomplete point clouds. Existing completion networks often require a vast number of parameters and substantial computational costs to achieve a high performance level, which may limit their practical application. In this work, we propose a novel Adaptive efficient Recurrent Forward Network (ARFNet), which is composed of three parts: Recurrent Feature Extraction (RFE), Forward Dense Completion (FDC) and Raw Shape Protection (RSP). In an RFE, multiple short global features are extracted from incomplete point clouds, while a dense quantity of completed results are generated in a coarse-to-fine pipeline in the FDC. Finally, we propose the Adamerge module to preserve the details from the original models by merging the generated results with the original incomplete point clouds in the RSP. In addition, we introduce the Sampling Chamfer Distance to better capture the shapes of the models and the balanced expansion constraint to restrict the expansion distances from coarse to fine. According to the experiments on ShapeNet and KITTI, our network can achieve state-of-the-art completion performances on dense point clouds with fewer parameters, smaller model sizes, lower memory costs and a faster convergence.
Keyword:
3D point clouds
recurrent structure
highly efficient completion
期刊
IF:
9.7
论文数:
4.6K
被引数:
2.4W
机构
引用论文
.png){kind=icon}
分享收藏Deep-PCAC: An End-to-End Deep Lossy Compression Framework for Point Cloud AttributesDeep-pcac: 点云属性的端到端深度有损压缩框架
PREAI
分享收藏
查看更多内容