AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning Canonical Embeddings for Unsupervised Shape Correspondence With Locally Linear Transformations

Pan Li He, Patrick Emami, Sanjay Ranka, Anand Rangarajan

TPAMI 2023 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence

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 the mapping smoothness loss E_r to DPC (ablation)DPC · SURREAL/SHRECaccuracy: 11.4% -> 17.7%Improved
add the mapping smoothness loss E_r to LTENet (ablation)LTENet · SURREAL/SHRECaccuracy: 20.6% -> 20.7%No clear effect
add cross-reconstruction to self-reconstruction (ablation)LTENet · SURREAL/SHRECaccuracy: 2.3% -> 20.6%Improved
add self-reconstruction to cross-reconstruction (ablation)LTENet · SURREAL/SHRECerror: 6.5 -> 5.9Improved
add E_r with lambda_reg=10 to self and cross losses (ablation)LTENet · SURREAL/SHRECerror: 5.9 -> 5.8Improved
use CS divergence instead of Chamfer distance (ablation)LTENet · SURREAL/SHRECaccuracy: 13.9% -> 20.7%Improved
use CS divergence instead of Earth mover's distance (ablation)LTENet · SURREAL/SHRECaccuracy: 19.6% -> 20.7%Improved
use LTENet instead of DPCcorrespondence learning · SURREAL/SHRECaccuracy: 17.7% -> 20.7%Improved
use LTENet instead of DPCcorrespondence learning · SMAL/TOSCAaccuracy: 33.2% -> 38.1%Improved
use LTENet instead of DPCcorrespondence learning · SHREC/SHRECaccuracy: 15.3% -> 14.3%No clear effect
apply optimal global linear transformation to learned embeddings (SMAL/TOSCA) (ablation)DPC embeddings · SMAL/TOSCAaccuracyHurt
apply optimal global linear transformation to learned embeddings (ablation)LTENet · SURREAL/SHREC and SMAL/TOSCAaccuracyImproved

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