Meta Architecture for Point Cloud Analysis
This provides a meta-architecture for researchers in 3D point cloud analysis to unify and compare methods, though it is incremental as it builds on existing approaches.
The paper tackles the lack of a unified framework for comparing 3D point cloud analysis networks by proposing PointMeta, which enables systematic analysis and leads to PointMetaBase, a building block that improves state-of-the-art mIoU by 0.7%/1.4%/2.1% with only 2%/11%/13% of computation cost on S3DIS datasets.
Recent advances in 3D point cloud analysis bring a diverse set of network architectures to the field. However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field. In this paper, we take the initiative to explore and propose a unified framework called PointMeta, to which the popular 3D point cloud analysis approaches could fit. This brings three benefits. First, it allows us to compare different approaches in a fair manner, and use quick experiments to verify any empirical observations or assumptions summarized from the comparison. Second, the big picture brought by PointMeta enables us to think across different components, and revisit common beliefs and key design decisions made by the popular approaches. Third, based on the learnings from the previous two analyses, by doing simple tweaks on the existing approaches, we are able to derive a basic building block, termed PointMetaBase. It shows very strong performance in efficiency and effectiveness through extensive experiments on challenging benchmarks, and thus verifies the necessity and benefits of high-level interpretation, contrast, and comparison like PointMeta. In particular, PointMetaBase surpasses the previous state-of-the-art method by 0.7%/1.4/%2.1% mIoU with only 2%/11%/13% of the computation cost on the S3DIS datasets.