FatNet: A Feature-attentive Network for 3D Point Cloud Processing

Research output: Chapter in Book/Report/Conference proceedingConference contribution


The application of deep learning to 3D point clouds is challenging due to its lack of order. Inspired by the point embeddings of PointNet and the edge embeddings of DGCNNs, we propose three improvements to the task of point cloud analysis. First, we introduce a novel feature-attentive neural network layer, a FAT layer, that combines both global point-based features and local edge-based features in order to generate better embeddings. Second, we find that applying the same attention mechanism across two different forms of feature map aggregation, max pooling and average pooling, gives better performance than either alone. Third, we observe that residual feature reuse in this setting propagates information more effectively between the layers, and makes the network easier to train. Our architecture achieves state-of-the-art results on the task of point cloud classification, as demonstrated on the ModelNet40 dataset, and an extremely competitive performance on the ShapeNet part segmentation challenge.
Original languageEnglish
Title of host publication25th International Conference on Pattern Recognition
Publication statusPublished - 10 Jan 2021
Event25th International Conference on Pattern Recognition - Milan, Italy
Duration: 10 Jan 202115 Jan 2021


Conference25th International Conference on Pattern Recognition
Abbreviated titleICPR 2020
Internet address


  • 3D Point Cloud, deep network, 3D shape classification, 3D shape retrieval, 3D shape segmentation

Cite this