AI Paper Atlas

Research map / 3D vision / Human pose estimation

Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction

Maosen Li, Siheng Chen, Zijing Zhang, Lingxi Xie, Qi Tian, Ya Zhang

ECCV 2022 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 94 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 cross-part bipartite interaction (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 111.74 -> 109.64Improved
split body upper-lower instead of left-right (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 110.16 -> 109.64Improved
use learned spectrum aggregation instead of channel averaging (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 112.14 -> 109.64Improved
use learned spectrum aggregation instead of self-attention (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 114.08 -> 109.64Improved
add skip-connection across the model (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 115.22 -> 109.64Improved
increase spectral channels from 1 to 3 (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 113.15 -> 109.64Improved
increase spectral channels from 3 to 5 (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 109.64 -> 110.52Hurt
use 2 scattering layers instead of 1 (10 MPGSBs) (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 111.29 -> 109.64Improved
use 10 MPGSBs instead of 8 (ablation)SPGSN · Human3.6M average, 1000 msMPJPE: 112.29 -> 109.64Improved
add body-part decomposition (SPGSN vs 1body) (ablation)SPGSN · Human3.6M average, 400 msMPJPE: 60.96 -> 58.26Improved
SPGSN vs strongest baseline HisRepSPGSN · Human3.6M average, 400 msMPJPE: 60.78 -> 58.26Improved
SPGSN vs strongest baseline on 3DPWSPGSN · 3DPW average, 1000 msMPJPE: 112.22 -> 111.05Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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