Shape and Symmetry Induction for 3D Objects

TL;DR

This paper introduces a method that leverages classification-trained models to predict 3D shape cues like surface normals and symmetry planes, enabling accurate 3D shape recovery of unseen objects from images.

Contribution

It repurposes existing classification models for 3D shape understanding by predicting surface normals and symmetry, facilitating shape extrapolation from limited views.

Findings

Accurately recovers 3D shape for unseen object classes.

Works on both synthetic and real images.

Enables extrapolation of occluded surfaces.

Abstract

Actions as simple as grasping an object or navigating around it require a rich understanding of that object's 3D shape from a given viewpoint. In this paper we repurpose powerful learning machinery, originally developed for object classification, to discover image cues relevant for recovering the 3D shape of potentially unfamiliar objects. We cast the problem as one of local prediction of surface normals and global detection of 3D reflection symmetry planes, which open the door for extrapolating occluded surfaces from visible ones. We demonstrate that our method is able to recover accurate 3D shape information for classes of objects it was not trained on, in both synthetic and real images.