.png){kind=icon}
返回
Continuous conditional random field convolution for point cloud segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2021.108357.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Point cloud segmentation is the foundation of 3D environmental perception for modern intelligent sys-tems. To solve this problem and image segmentation, conditional random fields (CRFs) are usually for-mulated as discrete models in label space to encourage label consistency, which is actually a kind of postprocessing. In this paper, we reconsider the CRF in feature space for point cloud segmentation be -cause it can capture the structure of features well to improve the representation ability of features rather than simply smoothing. Therefore, we first model the point cloud features with a continuous quadratic energy model and formulate its solution process as a message-passing graph convolution, by which it can be easily integrated into a deep network. We theoretically demonstrate that the message passing in the graph convolution is equivalent to the mean-field approximation of a continuous CRF model. Further-more, we build an encoder-decoder network based on the proposed continuous CRF graph convolution (CRFConv), in which the CRFConv embedded in the decoding layers can restore the details of high-level features that were lost in the encoding stage to enhance the location ability of the network, thereby benefiting segmentation. Analogous to the CRFConv, we show that the classical discrete CRF can also work collaboratively with the proposed network via another graph convolution to further improve the segmentation results. Experiments on various point cloud benchmarks demonstrate the effectiveness and robustness of the proposed method. Compared with the state-of-the-art methods, the proposed method can also achieve competitive segmentation performance. (c) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Point cloud segmentation
Conditional random fields
Message passing
Graph convolution
Mean-field approximation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
A fusion network for road detection via spatial propagation and spatial transformation基于空间传播和空间变换的道路检测融合网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Feature fusion network based on attention mechanism for 3D semantic segmentation of point clouds基于注意力机制的特征融合网络点云三维语义分割
PREAI
分享收藏Technical considerations in obtaining platelet rich fibrin for clinical and periodontal researchOAAI
OAAI分享收藏The effect of spin dilution on magnetism of the linear chain system β-Cu2−x Zn x V2O7自旋稀释对线性链体系 β-cu2-x Zn x V2O7磁性的影响Pramana
PramanaIF0
PREAI
分享收藏
查看更多内容