AI Paper Atlas

Research map / Video / Video generation

PoseAnything: General Pose-guided Video Generation with Part-aware Temporal Coherence

Ruiyan Wang, Teng Hu, Kaihui Huang, Zihan Su, Ran Yi, Lizhuang Ma

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control

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 Part-aware Temporal Coherence Module over channel-concat baseline (ablation)PoseAnything · XPose-benchmarkFVD: 102.30 -> 99.970Improved
use part segmentation and matching instead of whole-object cross-attention (ablation)PTCM · XPose-benchmarkFVD: 101.50 -> 99.970Improved
whole-object cross-attention (EC) versus no coherence module (ablation)PoseAnything · XPose-benchmarkPSNR: 29.85 -> 30.27Improved
inject pose by channel concatenation rather than MLP (ablation)PoseAnything (no PTCM) · TikTokFVD: 283.79 -> 133.95Improved
inject pose by channel concatenation rather than width concatenation (ablation)PoseAnything (no PTCM) · TikTokFVD: 415.13 -> 133.95Improved
reduce pose injection from 100% to 10% of frames (sparse training) (ablation)PoseAnything · XPose-benchmarkFVD: 99.97 -> 97.02No clear effect
reduce pose injection to 2.5% of frames (ablation)PoseAnything · XPose-benchmarkSSIM: 0.7114 -> 0.6757Hurt
raise CFG scale from 1.2 to 5.0 under dense pose (ablation)PoseAnything · XPose-benchmark (dense)PSNR: 30.61 -> 29.92Hurt
raise CFG scale from 1.2 to 5.0 under sparse pose (ablation)PoseAnything · XPose-benchmark (sparse)PSNR: 30.68 -> 29.84Hurt
train on XPose non-human data and use skeleton conditioning vs drag-based methodsPoseAnything · XPose-benchmark (non-human)LPIPS: 0.3530 -> 0.3241Improved
PoseAnything vs Animate-X on human videosPoseAnything · TikTok (human)FVD: 139.01 -> 133.95Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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