Skip to yearly menu bar Skip to main content


Poster

An Explicit Frame Construction for Normalizing 3D Point Clouds

Justin Baker · Shih-Hsin Wang · Tommaso de Fernex · Bao Wang

Hall C 4-9 #2700
[ ] [ Paper PDF ]
Wed 24 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

Many real-world datasets are represented as 3D point clouds -- yet they often lack a predefined reference frame, posing a challenge for machine learning or general data analysis. Traditional methods for determining reference frames and normalizing 3D point clouds often struggle with specific inputs, lack theoretical guarantees, or require massive data. We introduce a new algorithm that overcomes these limitations and guarantees both universality and compatibility with any learnable framework for 3D point cloud analysis. Our algorithm works with any input point cloud and performs consistently regardless of input complexities, unlike data-driven methods that are susceptible to biases or limited training data. Empirically, our algorithm outperforms existing methods in effectiveness and generalizability across diverse benchmark datasets. Code is available at https://github.com/Utah-Math-Data-Science/alignment.

Chat is not available.