Pith. sign in

REVIEW

Geometric Capsule Autoencoders for 3D Point Clouds

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1912.03310 v1 pith:VOGLHFIX submitted 2019-12-06 cs.LG cs.CVcs.GRcs.NEstat.ML

Geometric Capsule Autoencoders for 3D Point Clouds

classification cs.LG cs.CVcs.GRcs.NEstat.ML
keywords objectgeometricposecapsulefeaturecanonicalcapsulesclouds
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, such as an object or a part, and consists of two components: a pose and a feature. The pose encodes where the entity is, while the feature encodes what it is. We use these capsules to construct a Geometric Capsule Autoencoder that learns to group 3D points into parts (small local surfaces), and these parts into the whole object, in an unsupervised manner. Our novel Multi-View Agreement voting mechanism is used to discover an object's canonical pose and its pose-invariant feature vector. Using the ShapeNet and ModelNet40 datasets, we analyze the properties of the learned representations and show the benefits of having multiple votes agree. We perform alignment and retrieval of arbitrarily rotated objects -- tasks that evaluate our model's object identification and canonical pose recovery capabilities -- and obtained insightful results.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.