Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling
This work addresses a bottleneck in point cloud processing for applications like 3D vision, though it appears incremental as it builds on existing networks.
The paper tackles the problem of information loss in point cloud feature learning due to sampling and max pooling, which hinders representation of local context and fine shapes, by proposing PointStack with multi-resolution feature learning and learnable pooling, achieving state-of-the-art results in feature learning on point clouds.
Existing point cloud feature learning networks often incorporate sequences of sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation to learn high-semantic point features that represent the global context of a point cloud. Unfortunately, the compounded loss of information concerning granularity and non-maximum point features due to sampling and max pooling could adversely affect the high-semantic point features from existing networks such that they are insufficient to represent the local context of a point cloud, which in turn may hinder the network in distinguishing fine shapes. To cope with this problem, we propose a novel point cloud feature learning network, PointStack, using multi-resolution feature learning and learnable pooling (LP). The multi-resolution feature learning is realized by aggregating point features of various resolutions in the multiple layers, so that the final point features contain both high-semantic and high-resolution information. On the other hand, the LP is used as a generalized pooling function that calculates the weighted sum of multi-resolution point features through the attention mechanism with learnable queries, in order to extract all possible information from all available point features. Consequently, PointStack is capable of extracting high-semantic point features with minimal loss of information concerning granularity and non-maximum point features. Therefore, the final aggregated point features can effectively represent both global and local contexts of a point cloud. In addition, both the global structure and the local shape details of a point cloud can be well comprehended by the network head, which enables PointStack to advance the state-of-the-art of feature learning on point clouds. The codes are available at https://github.com/kaist-avelab/PointStack.