AI Paper Atlas

Research map / Video / Video generation

MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance

Quanhao Li, Zhen Xing, Rui Wang, Hui Zhang, Qi Dai, Zuxuan Wu

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 41 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
train on MagicData instead of MeViS+MOSE (ablation)MagicMotion Stage2 · MagicBenchMask IoU (%): 73.39 -> 76.61Improved
train on MagicData instead of MeViS+MOSE (ablation)MagicMotion Stage2 · MagicBenchFID: 24.24 -> 15.17Improved
use progressive dense-to-sparse training instead of training boxes from scratch (ablation)MagicMotion Stage2 · DAVISBox IoU (%): 67.34 -> 72.84Improved
use progressive dense-to-sparse training instead of training boxes from scratch (ablation)MagicMotion Stage2 · MagicBenchMask IoU (%): 74.61 -> 76.61Improved
add latent segment loss (ablation)MagicMotion Stage2 · DAVISMask IoU (%): 49.19 -> 53.94Improved
add latent segment loss (ablation)MagicMotion Stage2 · MagicBenchBox IoU (%): 78.02 -> 81.45Improved
move from mask control (Stage1) to box control (Stage2)MagicMotion CogVideoX · MagicBenchMask IoU (%): 91.57 -> 76.61Hurt
MagicMotion vs best prior method on MagicBench mask accuracyMagicMotion Stage1 CogVideoX · MagicBenchMask IoU (%): 68.78 -> 91.57Improved
MagicMotion vs best prior FVD on MagicBenchMagicMotion Stage2 CogVideoX · MagicBenchFVD: 168.82 -> 107.21Improved

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