AI Paper Atlas

Research map / 3D vision / Human pose estimation

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

Zhitao Yang, Zhongang Cai, Haiyi Mei, Shuai Liu, Zhaoxi Chen, Weiye Xiao, Yukun Wei, Zhongfei Qing, Chen Wei, Bo Dai, Wayne Wu, Chen Qian and 3 more

ICCV 2023 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 50 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 SynBody to real training dataHMR · 3DPW testMPJPE: 112.30 -> 95.01Improved
add SynBody to real training dataSPIN · 3DPW testMPJPE: 96.90 -> 84.14Improved
add SynBody to real training dataPARE · 3DPW testMPJPE: 81.79 -> 78.98Improved
add SynBody to real training dataVIBE · 3DPW testMPJPE: 94.88 -> 93.04Improved
add SynBody to real training dataHMR · AGORA valMPJPE: 226.71 -> 199.51Improved
use SynBody-100K instead of AGORA as added synthetic dataHMR · 3DPW testMPJPE: 101.61 -> 95.28Improved
use SynBody-100K instead of AGORA as added synthetic dataPARE · 3DPW testMPJPE: 85.34 -> 79.42Improved
replace SMPL-XL layered model with SURREAL-style texture-only rendering (ablation)PARE with SynBody-100K · 3DPW testMPJPE: 79.4 -> 82.2Hurt
add SynBody-100K SURREAL-style data to real data (ablation)PARE · 3DPW testMPJPE: 81.8 -> 82.2No clear effect
add SynBody (600K) to real dataOSX · AGORA val SMPL-XPVE (All): 168.6 -> 155.8Improved
add SynBody (600K) to real dataOSX · 3DPW test bodyMPJPE: 110.2 -> 92.2Improved
increase amount of SynBody training data (ablation)HMR trained from scratch · 3DPW testerrorImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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