AI Paper Atlas

Research map / 3D vision / Face and shape

Gait Recognition in the Wild With Dense 3D Representations and a Benchmark

CVPR 2022 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 256 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 3D branch to the silhouette-only model (ablation)SMPLGait · Gait3D, 88×128 inputRank-1 (%): 47.70 -> 53.20Helped
add the 3D branch to the silhouette-only model (ablation)SMPLGait · Gait3D, 44×64 inputRank-1 (%): 42.90 -> 46.30Helped
use larger 88×128 rather than 44×64 inputSMPLGait · Gait3DRank-1 (%): 46.30 -> 53.20Helped
train GaitSet on Gait3D rather than GREWGaitSet · GREWRank-1 (%): 16.50 -> 43.86Helped
train GaitSet on CASIA-B rather than Gait3DGaitSet · Gait3DRank-1 (%): 6.90Hurt
train GaitSet on OU-LP rather than Gait3DGaitSet · Gait3DRank-1 (%): 6.10Hurt
increase the number of training framesgait recognition models on Gait3D · Gait3DRank-1 accuracyMixed
increase the number of training IDsgait recognition models on Gait3D · Gait3DaccuracyHelped
use longer test sequencesgait recognition models on Gait3D · Gait3D test setaccuracyHelped

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