Symmetry-Robust 3D Orientation Estimation

TL;DR

This paper presents a novel two-stage pipeline for 3D shape orientation estimation, achieving state-of-the-art results on all ShapeNet classes by overcoming fundamental symmetry-related challenges.

Contribution

The authors introduce a comprehensive orientation estimation method trained on all ShapeNet classes, addressing symmetry issues and improving accuracy over previous approaches.

Findings

State-of-the-art performance on up-axis estimation.

Effective full-orientation estimation across all ShapeNet classes.

Theoretical insights into symmetry obstacles in orientation estimation.

Abstract

Orientation estimation is a fundamental task in 3D shape analysis which consists of estimating a shape's orientation axes: its side-, up-, and front-axes. Using this data, one can rotate a shape into canonical orientation, where its orientation axes are aligned with the coordinate axes. Developing an orientation algorithm that reliably estimates complete orientations of general shapes remains an open problem. We introduce a two-stage orientation pipeline that achieves state of the art performance on up-axis estimation and further demonstrate its efficacy on full-orientation estimation, where one seeks all three orientation axes. Unlike previous work, we train and evaluate our method on all of Shapenet rather than a subset of classes. We motivate our engineering contributions by theory describing fundamental obstacles to orientation estimation for rotationally-symmetric shapes, and show how our method avoids these obstacles.