PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

TL;DR

PointTree is a novel point cloud encoder that uses relaxed K-D trees and PCA-based normalization to achieve transformation robustness, significantly improving performance in 3D understanding tasks under geometric distortions.

Contribution

We introduce PointTree, a transformation-robust point cloud encoder utilizing relaxed K-D trees and PCA-based pre-alignment, advancing 3D representation learning.

Findings

Outperforms state-of-the-art methods on transformed datasets

Achieves higher accuracy in object classification and segmentation

Demonstrates robustness to various geometric distortions

Abstract

Being able to learn an effective semantic representation directly on raw point clouds has become a central topic in 3D understanding. Despite rapid progress, state-of-the-art encoders are restrictive to canonicalized point clouds, and have weaker than necessary performance when encountering geometric transformation distortions. To overcome this challenge, we propose PointTree, a general-purpose point cloud encoder that is robust to transformations based on relaxed K-D trees. Key to our approach is the design of the division rule in K-D trees by using principal component analysis (PCA). We use the structure of the relaxed K-D tree as our computational graph, and model the features as border descriptors which are merged with pointwise-maximum operation. In addition to this novel architecture design, we further improve the robustness by introducing pre-alignment -- a simple yet effective PCA-based normalization scheme. Our PointTree encoder combined with pre-alignment consistently outperforms state-of-the-art methods by large margins, for applications from object classification to semantic segmentation on various transformed versions of the widely-benchmarked datasets. Code and pre-trained models are available at https://github.com/immortalCO/PointTree.