AI Paper Atlas

Research map / 3D vision / Human pose estimation

DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior

Junzhe Lu, Jing Lin, Hongkun Dou, Ailing Zeng, Yue Deng, Xian Liu, Zhongang Cai, Lei Yang, Yulun Zhang, Haoqian Wang, Ziwei Liu

ICCV 2025 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 14 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
use truncated timestep scheduling instead of uniform scheduling (ablation)DPoser-X · ARCTIC whole-body mesh recoveryPA-MPVPE (all): 62.13 -> 60.98Improved
use truncated timestep scheduling instead of fixed scheduling (ablation)DPoser · AMASS motion denoising (40 mm noise)MPJPE: 22.54 -> 19.87Improved
use truncated timestep scheduling instead of random scheduling (ablation)DPoser · AMASS motion denoising (40 mm noise)MPJPE: 23.87 -> 19.87Improved
use truncated timestep scheduling instead of random scheduling (ablation)DPoser-X · ARCTIC whole-body mesh recoveryPA-MPVPE (hands): 16.63 -> 15.60Improved
replace one-step denoiser with 5-step denoising (ablation)DPoser-X · ARCTIC whole-body mesh recoveryPA-MPVPE (all): 60.98 -> 61.39Hurt
replace one-step denoiser with 10-step denoising (ablation)DPoser · AMASS motion denoisingMPJPE: 19.87 -> 21.34Hurt
add the mixed training strategy (versus fused-only) (ablation)DPoser-X · Fit3D whole-body mesh recoveryPA-MPVPE (hands): 18.12 -> 15.83Improved
add fused module to base part models (ablation)DPoser-X · ARCTIC whole-body pose completionmin MPVPE: 25.49 -> 21.51Improved
use mixed instead of fused trainingDPoser-X · whole-body pose generationFID: 3.71 -> 13.97Hurt
use mixed instead of fused training (ablation)DPoser-X · BEAT2 whole-body pose completionmin MPVPE: 15.51 -> 15.92No clear effect
use wider timestep range [0.2, 0.05] for noisier input (ablation)DPoser · AMASS motion denoising (100 mm noise)MPJPE: 36.13 -> 34.15Improved
use truncated scheduling on images instead of standardDPoser · ImageNet image inpaintingvisual qualityHurt

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