Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network

11/06/2018
by   Xinhai Liu, et al.
2

Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to capture fine-grained contextual information in hand-crafted or explicit manners, such as the correlation between different areas in a local region, which limits the discriminative ability of learned features. To resolve this issue, we propose a novel deep learning model for 3D point clouds, named Point2Sequence, to learn 3D shape features by capturing fine-grained contextual information in a novel implicit way. Point2Sequence employs a novel sequence learning model for point clouds to capture the correlations by aggregating multi-scale areas of each local region with attention. Specifically, Point2Sequence first learns the feature of each area scale in a local region. Then, it captures the correlation between area scales in the process of aggregating all area scales using a recurrent neural network (RNN) based encoder-decoder structure, where an attention mechanism is proposed to highlight the importance of different area scales. Experimental results show that Point2Sequence achieves state-of-the-art performance in shape classification and segmentation tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8

research
03/18/2020

LRC-Net: Learning Discriminative Features on Point Clouds by EncodingLocal Region Contexts

Learning discriminative feature directly on point clouds is still challe...
research
08/02/2019

L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention

Auto-encoder is an important architecture to understand point clouds in ...
research
03/18/2020

LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts

Learning discriminative feature directly on point clouds is still challe...
research
06/07/2017

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Few prior works study deep learning on point sets. PointNet by Qi et al....
research
08/29/2019

Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules

Learning discriminative shape representation directly on point clouds is...
research
12/02/2020

PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds

In this paper, we propose Point-Voxel Recurrent All-Pairs Field Transfor...
research
07/23/2019

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Atrous Convolution for Point Clouds

Motivated by the success of encoding multi-scale contextual information ...

Please sign up or login with your details

Forgot password? Click here to reset