AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Dense Correspondences between Human Bodies via Learning Transformation Synchronization on Graphs

Xiangru Huang, Haitao Yang, Etienne Vouga, Qixing Huang

NeurIPS 2020 · Graph learning › Graph algorithms and clustering · approach: Graph embedding and spectral sparsification · 5 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 learned transformation synchronization on top of initial transformations (ablation)Ours-Desc · SURREALaverage correspondence error (cm): 2.19 -> 1.71Improved
add learned transformation synchronization on top of initial transformations (ablation)Ours-Desc · FAUSTaverage correspondence error (cm): 2.59 -> 1.90Improved
add learned transformation synchronization on top of initial transformations (ablation)Ours-Desc · SHREC19average correspondence error (cm): 5.84 -> 4.81Improved
use generic convex optimization instead of learned regularization (ablation)Ours-Refine · SURREALaverage correspondence error (cm): 1.71 -> 2.13Hurt
use generic convex optimization instead of learned regularization (ablation)Ours-Refine · FAUSTaverage correspondence error (cm): 1.90 -> 2.44Hurt
use generic convex optimization instead of learned regularization (ablation)Ours-Refine · SHREC19average correspondence error (cm): 4.81 -> 5.77Hurt
replace learned regularization with ASAP deformationOurs-Refine · SURREALaverage correspondence error (cm): 1.71 -> 1.93Hurt
replace learned regularization with ASAP deformationOurs-Refine · SHREC19average correspondence error (cm): 4.81 -> 6.15Hurt
replace learned regularization with SMPL fittingOurs-Refine · FAUSTaverage correspondence error (cm): 1.90 -> 1.98Hurt
replace Laplacian embedding descriptor with SHOTOurs-Desc · SURREALaverage correspondence error (cm): 2.19 -> 5.97Hurt
replace Laplacian embedding descriptor with SHOTOurs-Desc · SHREC1910cm recall: 0.965 -> 0.840Hurt
replace Laplacian embedding descriptor with HKSOurs-Desc · FAUSTaverage correspondence error (cm): 2.59 -> 9.98Hurt

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