AI Paper Atlas

Research map / Video / Video generation

Training-free Controllable Motion Generation under Heterogeneous Constraints

Xiaofei Hui, Bo Yan, Haoxuan Qu, Hossein Rahmani, Jun Liu

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
use forward-evaluation control for criterion constraints instead of surrogate gradients (ablation)MIC · HSI-2unsuccess rate: 0.219 -> 0.094Improved
use unified handling of both constraint types vs separate (ablation)MIC · HSI-2sim pass rate: 0.656 -> 0.875Improved
add feedback regulator (ablation)MIC · HSI-2sim pass rate: 0.813 -> 0.875Improved
add control allocator (ablation)MIC · HSI-2constraint error: 0.048 -> 0.009Improved
add full coordination mechanism (ablation)MIC · HSI-2sim pass rate: 0.688 -> 0.875Improved
MIC vs best gradient baselinesMIC · GEO-1 (open-set)unsuccess rate: 0.531 -> 0.094Improved
MIC vs baselines on motion qualityMIC · HSI-1 (known)FID: 0.556 -> 0.494Improved
MIC vs IK on skatingMIC · HSI-2 (open-set)foot skating: 0.253 -> 0.172Improved

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