AI Paper Atlas

Research map / 3D vision / Face and shape

Deep Virtual Markers for Articulated 3D Shapes

Hyomin Kim, Jungeon Kim, Jaewon Kam, Jaesik Park, Seungyong Lee

ICCV 2021 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 7 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 multiview aggregation (72 rendered depth views) instead of one-shot inferenceDeep virtual markers · FAUST challenge intra-subjecterror (cm): 1.417 -> 1.185Improved
use multiview aggregation instead of one-shot inferenceDeep virtual markers · FAUST challenge inter-subjecterror (cm): 2.495 -> 2.372Improved
use multiview aggregation instead of one-shot inferenceDeep virtual markers · FAUST training pairs worst error, inter-subjectworst-pair error (cm): 4.56 -> 3.25Improved
use multiview aggregation instead of one-shot inferenceDeep virtual markers · FAUST partial-to-partial inter-subject worst errorworst-pair error (cm): 16.06 -> 11.166Improved
use multiview aggregation instead of one-shot inferenceDeep virtual markers · Ren et al. dataset S / Fnormalized mean geodesic error (%): 3.1 -> 1.9Improved
use multiview aggregation instead of one-shot inferenceDeep virtual markers · FAUST full-to-partial intra-subjectaverage error (cm): 2.41 -> 2.39No clear effect
train on soft geodesic labels instead of hard one-hot labels (ablation)Deep virtual markers · Marker weight smoothness (qualitative)visual smoothnessImproved
replace DHBC with deep virtual markers (multiview)Full-to-full correspondence · FAUST training pairs intra-subject worst errorworst-pair error (cm): 9.98 -> 2.76Improved
replace DHBC with deep virtual markers (multiview)Partial-to-partial correspondence · FAUST P2P intra-subjectaverage error (cm): 9.51 -> 3.40Improved
replace DHBC with deep virtual markers (oneshot)Full-to-full correspondence · FAUST training pairs intra-subject average erroraverage error (cm): 2.00 -> 2.26Hurt
train on SCAPE only and test on FAUST (limited shape variety), versus F / F (ablation)3D-CODED · Ren et al. datasetnormalized mean geodesic error (%): 2.5 -> 33.0Hurt

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