SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images

by   Yifei Shi, et al.

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.


page 1

page 10

page 12

page 13


Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild

We propose a method to learn 3D deformable object categories from raw si...

Scale space radon transform-based inertia axis and object central symmetry estimation

Inertia Axes are involved in many techniques for image content measureme...

SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

In this paper, we establish a baseline for object symmetry detection in ...

Im2Struct: Recovering 3D Shape Structure from a Single RGB Image

We propose to recover 3D shape structures from single RGB images, where ...

SRN: Side-output Residual Network for Object Reflection Symmetry Detection and Beyond

In this paper, we establish a baseline for object reflection symmetry de...

Learning-based Real-time Detection of Intrinsic Reflectional Symmetry

Reflectional symmetry is ubiquitous in nature. While extrinsic reflectio...

A Framework for Symmetric Part Detection in Cluttered Scenes

The role of symmetry in computer vision has waxed and waned in importanc...

Please sign up or login with your details

Forgot password? Click here to reset