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

by   Xinhai Liu, et al.

Auto-encoder is an important architecture to understand point clouds in an encoding and decoding procedure of self reconstruction. Current auto-encoder mainly focuses on the learning of global structure by global shape reconstruction, while ignoring the learning of local structures. To resolve this issue, we propose Local-to-Global auto-encoder (L2G-AE) to simultaneously learn the local and global structure of point clouds by local to global reconstruction. Specifically, L2G-AE employs an encoder to encode the geometry information of multiple scales in a local region at the same time. In addition, we introduce a novel hierarchical self-attention mechanism to highlight the important points, scales and regions at different levels in the information aggregation of the encoder. Simultaneously, L2G-AE employs a recurrent neural network (RNN) as decoder to reconstruct a sequence of scales in a local region, based on which the global point cloud is incrementally reconstructed. Our outperforming results in shape classification, retrieval and upsampling show that L2G-AE can understand point clouds better than state-of-the-art methods.


page 1

page 2

page 3

page 4

page 5

page 6

page 8

page 9


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

Exploring contextual information in the local region is important for sh...

NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler

Most algorithms that rely on deep learning-based approaches to generate ...

Probabilistic Point Cloud Reconstructions for Vertebral Shape Analysis

We propose an auto-encoding network architecture for point clouds (PC) c...

Self-Supervised Point Cloud Representation Learning with Occlusion Auto-Encoder

Learning representations for point clouds is an important task in 3D com...

Context-Aware Transformer for 3D Point Cloud Automatic Annotation

3D automatic annotation has received increased attention since manually ...

HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization

Unsupervised anomaly detection and localization is a crucial task as it ...

Please sign up or login with your details

Forgot password? Click here to reset