AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Clothing and Pose Invariant 3D Shape Representation for Long-Term Person Re-Identification

Feng Liu, Minchul Kim, ZiAng Gu, Anil Jain, Xiaoming Liu

ICCV 2023 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 72 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 the 3D shape modules instead of classification loss only (ablation)3DInvarReID · CCDA (trained on Celeb-reID)Rank-1 (%): 28.4 -> 36.3Improved
add 3D clothing and texture modeling with rendering layer (ablation)3DInvarReID · CCDA (trained on Celeb-reID)Rank-1 (%): 32.1 -> 36.3Improved
add 3D pre-training stage (ablation)3DInvarReID · CCDA (trained on Celeb-reID)Rank-1 (%): 29.3 -> 36.3Improved
fuse 3D shape features with ReIDCaps by score summationReIDCaps · Celeb-reID-lightRank-1 (%): 33.5 -> 42.2Improved
fuse 3D shape features with CAL on CCVIDCAL · CCVID cloth-changingRank-1 (%): 81.7 -> 84.3Improved
fuse 3D shape features with CAL on short-term ReIDCAL · Market-1501 and MSMT17Rank-1 (%): 94.7 -> 95.1 (Market-1501), 79.7 -> 80.8 (MSMT17)Improved
use 3DInvarReID alone instead of CAL (single model, 2D features)cloth-changing ReID · CCVID cloth-changingRank-1 (%): 81.7 -> 70.2Hurt
use 3DInvarReID alone instead of CAL on LTCC and PRCCcloth-changing ReID · LTCC and PRCCRank-1 (%): 40.1 -> 37.8 (LTCC), 55.2 -> 51.6 (PRCC)Hurt
train on Celeb-reID and test cross-domain with 3DInvarReID vs CALcloth-changing ReID · PRCC (cross-domain)Rank-1 (%): 31.6 -> 40.7Improved
use 3DInvarReID naked-body shape fitting instead of SHAPY for reconstruction3D naked body reconstruction · HBW validationChamfer distance CD-L2: 0.632 -> 0.610Improved

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