AI Paper Atlas

Research map / Point clouds / Point cloud classification

Canonical Capsules: Self-Supervised Capsules in Canonical Pose

Weiwei Sun, Andrea Tagliasacchi, Boyang Deng, Sara Sabour, Soroosh Yazdani, Geoffrey Hinton, Kwang Moo Yi

NeurIPS 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 35 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add equivariance loss (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.16 -> 1.11Improved
add equivariance loss (ablation)Canonical Capsules · ShapeNet airplane unalignedmStd: 110.174 -> 8.278Improved
add localization loss (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.44 -> 1.11Improved
add equilibrium loss (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.60 -> 1.11Improved
add invariance loss (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.12 -> 1.11No clear effect
add canonical loss (ablation)Canonical Capsules · ShapeNet airplane unalignedmStd: 8.421 -> 8.278Improved
use ACNe backbone instead of PointNet (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.28 -> 1.11Improved
use 10 capsules instead of 5 (constant capacity) (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.25 -> 1.11Improved
use 10 capsules instead of 20 (constant capacity) (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.15 -> 1.11Improved
use learned canonicalizer instead of one-shot alignment (ablation)Canonical Capsules · ShapeNet chair unalignedChamfer distance: 2.92 -> 2.58Improved
use learned canonicalizer instead of one-shot alignment (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 1.10 -> 1.11No clear effect
re-extract descriptors after canonicalization (ablation)Canonical Capsules · ShapeNet airplane unalignedChamfer distance: 2.12 -> 1.08Improved

Later papers that compared with this method

1 later accepted paper reports Canonical Capsules as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy