AI Paper Atlas

Research map / 3D vision / Human pose estimation

Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence

Yutong Chen, Yifan Zhan, Zhihang Zhong, Wei Wang, Xiao Sun, Yu Qiao, Yinqiang Zheng

ECCV 2024 · 3D vision › Human pose estimation · approach: Physics and sensor-based motion capture · 9 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 current pose condition alongside delta pose sequence (ablation)Dyco · I3D-Human novel viewPSNR: 30.89 -> 31.22Improved
add delta pose sequence condition to pose-only model (ablation)Dyco · I3D-Human novel viewPSNR: 30.40 -> 31.22Improved
add delta pose sequence on top of nothing (no pose, no delta) (ablation)Dyco · I3D-Human novel viewDME: 5.21 -> 4.52Improved
add localized kinematic spatial dependency (ablation)Dyco · I3D-Human novel posePSNR: 29.58 -> 30.12Improved
add localized spatial dependency (ablation)Dyco · I3D-Human novel viewDME: 4.42 -> 4.52No clear effect
feed delta pose into canonical volume as well as non-rigid transform (ablation)Dyco · I3D-Human novel viewDME: 5.14 -> 4.52Improved
use delta pose sequence instead of absolute pose sequence (ablation)Dyco · I3D-Human novel viewPSNR: 29.93 -> 31.22Improved
use axis-angle instead of quaternion delta pose representation (ablation)Dyco · I3D-Human novel viewLPIPS x1000: 36.00 -> 34.54Improved
lengthen delta sequence from 6 to 12 frames (ablation)Dyco · I3D-Human novel posePSNR: 30.12 -> 29.69Hurt
shorten delta sequence from 6 to 2 frames (ablation)Dyco · I3D-Human novel posePSNR: 30.12 -> 29.89Hurt
reduce step s and s_d from 25 to 12 (ablation)Dyco · I3D-Human novel viewPSNR: 31.22 -> 30.99Hurt
use Dyco instead of 3DGS-Avatar on tightly clothed ZJU-MoCap novel poseDyco · ZJU-MoCap novel posePSNR: 30.01 vs 29.71No clear effect

Earlier methods this paper compares with

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