AI Paper Atlas

Research map / Video / Video generation

Kinematics-Agnostic 3D Human Motion Prediction via Equivariant Latent Diffusion

Cecilia Curreli, Florian Hofherr, Dominik Muhle, Abhishek Saroha, Riccardo Marin, Daniel Cremers

ECCV 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
break permutation equivariance by adding positional encoding over joints (ablation)EquiFusion · H36M zero-shot kinematicsADE: 0.380 -> 0.467Hurt
use equivariant architecture instead of joint-dependent weights with multi-dataset training (ablation)EquiFusion · H36M zero-shot kinematicsADE: 0.670 -> 0.380Improved
break equivariance, in-domain AMASS (ablation)EquiFusion · AMASSADE: 0.512 -> 0.539 ADE; MAE 6.525 -> 6.974Mixed
add explicit joint semantics (limb side or type) (ablation)EquiFusion · H36M zero-shot kinematicsADE: 0.380 -> 0.381No clear effect
add Nymeria to AMASS training data (ablation)EquiFusion · H36M zero-shot kinematicsuADE: 7.86 -> 7.71Improved
represent motion as bone directions instead of 3D positions (ablation)EquiFusion · AMASSADE: 0.501 -> 0.498 ADE; CMD 13.963 -> 12.530No clear effect
represent motion as bone directions instead of 3D positions (ablation)SkelDiff · AMASSADE: 0.480 -> 0.496 ADE; CMD 11.417 -> 9.143Mixed
natively handle partial kinematics versus heuristic completionEquiFusion · AMASS with random limb occludedADE: 0.567 -> 0.553 (A); 0.499 (A+N)Improved
EquiFusion versus SkelDiff on out-of-distribution MoYogaEquiFusion · MoYogaADE: 0.567 -> 0.501Improved
EquiFusion versus retargeted baselines in zero-shot H36M kinematicsEquiFusion · H36M zero-shot kinematicsFID: 5.252 -> 0.691 (vs SkelDiff)Improved

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