AI Paper Atlas

Research map / Video / Video generation

Unifying Precise Keyframes and Semantic Control via Multi-level Diffusion

Linjun Wu, Jiejia Yu, Leyang Jin, He Wang, Bowen Zheng, Xu Yang, Hao Jiang, Fei Xia, Fei Ling, Jun Deng, Xiaogang Jin

CVPR 2026 · Video › Video generation · approach: Text-to-motion diffusion

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
combine global and local keyframe guidance (ablation)multi-level diffusion model · HumanML3D keyframe in-betweeningKeyframe Error (cm): 3.709 -> 2.933 (vs LocG); 9.464 -> 2.933 (vs GloG)Improved
add global keyframe guidance to local guidance (ablation)multi-level diffusion model · HumanML3D keyframe in-betweeningSS Similarity: 0.751 -> 0.806Improved
add trajectory refinement (ablation)LocG + GloG · HumanML3D keyframe in-betweeningKeyframe Error (cm): 2.933 -> 0.667Improved
add trajectory refinement (ablation)LocG + GloG · HumanML3D keyframe in-betweeningFID: 0.037 -> 0.032Improved
add pose refinement (diffusion imputation) (ablation)LocG + GloG + TraR · HumanML3D keyframe in-betweeningKeyframe Error (cm): 0.667 -> 0.000Improved
add pose refinement (ablation)LocG + GloG + TraR · HumanML3D keyframe in-betweeningFID: 0.032 -> 0.023Improved
add pose refinement (ablation)LocG + GloG + TraR · HumanML3D keyframe in-betweeningSS Similarity: 0.807 -> 0.804No clear effect
use proportional-to-root-speed trajectory correction instead of uniform velocity adjustment (ablation)trajectory refinement · HumanML3D keyframe in-betweeningfoot skating / driftImproved
increase number of intermediate keyframes from K=0 to K=20 (ablation)multi-level diffusion model · HumanML3D keyframe sparsitySS Similarity / FID: SS 0.719 -> 0.833; FID 0.159 -> 0.004Improved
increase number of intermediate keyframes (ablation)multi-level diffusion model · HumanML3D keyframe sparsityR-Precision (Top 3): 0.796 -> 0.802No clear effect
use invert-and-sample editing with strict keyframe constraints instead of DNO latent optimizationmotion editing · HumanML3D pose editingFID: 1.798 -> 0.284Improved

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