Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds

TL;DR

This paper introduces a novel, efficient method for estimating reflective symmetry planes in 3D point clouds, using a recurrent 2D convolutional approach that performs well on both full and partial scans.

Contribution

It presents a new encoding and a recurrent regression scheme for symmetry estimation that avoids expensive 3D convolutions, enabling end-to-end processing of partial and full 3D scans.

Findings

Achieves accuracy comparable to state-of-the-art on synthetic data.

Effectively handles partial scans in real-world applications.

Improves 3D object detection outputs using symmetry estimation.

Abstract

Many man-made objects are characterised by a shape that is symmetric along one or more planar directions. Estimating the location and orientation of such symmetry planes can aid many tasks such as estimating the overall orientation of an object of interest or performing shape completion, where a partial scan of an object is reflected across the estimated symmetry plane in order to obtain a more detailed shape. Many methods processing 3D data rely on expensive 3D convolutions. In this paper we present an alternative novel encoding that instead slices the data along the height dimension and passes it sequentially to a 2D convolutional recurrent regression scheme. The method also comprises a differentiable least squares step, allowing for end-to-end accurate and fast processing of both full and partial scans of symmetric objects. We use this approach to efficiently handle 3D inputs to design a method to estimate planar reflective symmetries. We show that our approach has an accuracy comparable to state-of-the-art techniques on the task of planar reflective symmetry estimation on full synthetic objects. Additionally, we show that it can be deployed on partial scans of objects in a real-world pipeline to improve the outputs of a 3D object detector.