PointVector: A Vector Representation In Point Cloud Analysis
This work addresses a domain-specific problem in point cloud analysis by introducing a novel method for feature aggregation, offering an incremental improvement in efficiency and performance.
The paper tackles the limitation of standard MLPs in extracting local features for point cloud analysis by proposing a Vector-oriented Point Set Abstraction and a PointVector model, achieving state-of-the-art performance of 72.3% mIOU on S3DIS Area 5 and 78.4% mIOU on S3DIS with 58% of the parameters of PointNeXt.
In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance $\textbf{72.3\% mIOU}$ on the S3DIS Area 5 and $\textbf{78.4\% mIOU}$ on the S3DIS (6-fold cross-validation) with only $\textbf{58\%}$ model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon.