SymmetryNet: Learning to predict reflectional and rotational symmetries of 3D shapes from single-view RGB-D images

Yifei Shi, Junwen Huang, Hongjia Zhang, Xin Xu, Szymon Rusinkiewicz, Kai Xu

Research output: Contribution to journalArticlepeer-review

Abstract

We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image. Directly training a deep model for symmetry prediction, however, can quickly run into the issue of overfitting. We adopt a multi-task learning approach. Aside from symmetry axis prediction, our network is also trained to predict symmetry correspondences. In particular, given the 3D points present in the RGB-D image, our network outputs for each 3D point its symmetric counterpart corresponding to a specific predicted symmetry. In addition, our network is able to detect for a given shape multiple symmetries of different types. We also contribute a benchmark of 3D symmetry detection based on single-view RGB-D images. Extensive evaluation on the benchmark demonstrates the strong generalization ability of our method, in terms of high accuracy of both symmetry axis prediction and counterpart estimation. In particular, our method is robust in handling unseen object instances with large variation in shape, multi-symmetry composition, as well as novel object categories.

Original languageEnglish (US)
Article number213
JournalACM Transactions on Graphics
Volume39
Issue number6
DOIs
StatePublished - Nov 26 2020

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Keywords

  • counterpart prediction
  • neural networks
  • symmetry prediction

Fingerprint

Dive into the research topics of 'SymmetryNet: Learning to predict reflectional and rotational symmetries of 3D shapes from single-view RGB-D images'. Together they form a unique fingerprint.

Cite this