AI Paper Atlas

Research map / 3D vision / Face and shape

Learning 3D Keypoint Descriptors for Non-Rigid Shape Matching

Hanyu Wang, Jianwei Guo, Dong-Ming Yan, Weize Quan, Xiaopeng Zhang

ECCV 2018 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 40 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
use Min-CV triplet loss instead of classic triplet loss (ablation)triplet CNN descriptor · FAUSTP1% (CMC): 25.93 -> 40.42Improved
use Min-CV triplet loss instead of classic triplet loss (ablation)triplet CNN descriptor · FAUSTP20% (CMC): 57.82 -> 71.29Improved
use Min-CV triplet loss instead of Kumar's loss (ablation)triplet CNN descriptor · FAUSTP1% (CMC): 33.39 -> 40.42Improved
use Min-CV triplet loss instead of Kumar's loss (ablation)triplet CNN descriptor · FAUSTP20% (CMC): 66.25 -> 71.29Improved
use Min-CV triplet loss instead of Jan's loss (ablation)triplet CNN descriptor · FAUSTP1% (CMC): 12.28 -> 40.42Improved
use learned descriptor instead of MoNet when transferring across datasetsdescriptor · FAUSTP1% (CMC): 56.93 -> 49.14Hurt
use learned descriptor instead of FMNetdescriptor · SPRING (trained on FAUST)P1% (CMC): 13.40 -> 63.30Improved
use learned descriptor instead of FMNetdescriptor · FACE (trained on FAUST)P1% (CMC): 12.00 -> 35.22Improved
use learned descriptor instead of RoPSdescriptor · FACE (trained on FAUST)AP: 0.629 -> 0.619Mixed
use learned descriptor instead of LSCNNdescriptor · FAUSTP20% (CMC): 58.61 -> 81.70Improved

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