A Closer Look at Local Aggregation Operators in Point Cloud Analysis
This work addresses the need for clarity in point cloud processing by showing that complex operator designs may be unnecessary, benefiting researchers and practitioners in computer vision and 3D analysis.
The paper investigates the impact of local aggregation operators in point cloud analysis and finds that under consistent deep residual architectures, existing operators yield similar performance, leading to the proposal of a simple weight-free operator called Position Pooling (PosPool) that achieves state-of-the-art results, including a 7.4 mIoU improvement on PartNet datasets.
Recent advances of network architecture for point cloud processing are mainly driven by new designs of local aggregation operators. However, the impact of these operators to network performance is not carefully investigated due to different overall network architecture and implementation details in each solution. Meanwhile, most of operators are only applied in shallow architectures. In this paper, we revisit the representative local aggregation operators and study their performance using the same deep residual architecture. Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks. This finding stimulate us to rethink the necessity of sophisticated design of local aggregation operator for point cloud processing. To this end, we propose a simple local aggregation operator without learnable weights, named Position Pooling (PosPool), which performs similarly or slightly better than existing sophisticated operators. In particular, a simple deep residual network with PosPool layers achieves outstanding performance on all benchmarks, which outperforms the previous state-of-the methods on the challenging PartNet datasets by a large margin (7.4 mIoU). The code is publicly available at https://github.com/zeliu98/CloserLook3D