PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud

TL;DR

This paper introduces PIDS, a neural architecture search framework that jointly explores point interactions and dimensions to improve semantic segmentation of 3D point clouds, achieving better accuracy than existing models.

Contribution

PIDS is the first to jointly search for point interactions and dimensions, significantly enhancing 3D point cloud segmentation performance.

Findings

Achieved ~1% mIOU improvement on SemanticKITTI.

Outperformed state-of-the-art 3D models on S3DIS.

Demonstrated effective joint exploration of point features.

Abstract

The interaction and dimension of points are two important axes in designing point operators to serve hierarchical 3D models. Yet, these two axes are heterogeneous and challenging to fully explore. Existing works craft point operator under a single axis and reuse the crafted operator in all parts of 3D models. This overlooks the opportunity to better combine point interactions and dimensions by exploiting varying geometry/density of 3D point clouds. In this work, we establish PIDS, a novel paradigm to jointly explore point interactions and point dimensions to serve semantic segmentation on point cloud data. We establish a large search space to jointly consider versatile point interactions and point dimensions. This supports point operators with various geometry/density considerations. The enlarged search space with heterogeneous search components calls for a better ranking of candidate models. To achieve this, we improve the search space exploration by leveraging predictor-based Neural Architecture Search (NAS), and enhance the quality of prediction by assigning unique encoding to heterogeneous search components based on their priors. We thoroughly evaluate the networks crafted by PIDS on two semantic segmentation benchmarks, showing ~1% mIOU improvement on SemanticKITTI and S3DIS over state-of-the-art 3D models.