AI Paper Atlas

Research map / Video / Video generation

LAMP: Language-Assisted Motion Planning for Controllable Video Generation

Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra, Erkut Erdem, Aykut Erdem, Duygu Ceylan

CVPR 2026 · Video › Video generation · approach: Trajectory-guided motion control · 4 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
predict DSL motion programs instead of binned per-frame trajectories (ablation)LAMP · Procedural dataset test, free-form camera (DSL vs trajectory)coarse translation F1: 0.847 -> 0.996Improved
predict DSL motion programs instead of binned per-frame trajectories (ablation)LAMP · Procedural dataset test, free-form camera (DSL vs trajectory)fine translation F1: 0.781 -> 0.966Improved
predict DSL motion programs instead of binned per-frame trajectories (ablation)LAMP · Procedural dataset test, free-form camera (DSL vs trajectory)coarse rotation F1: 0.730 -> 0.950Improved
predict DSL motion programs instead of binned per-frame trajectories (ablation)LAMP · Procedural dataset test, free-form camera (DSL vs trajectory)fine rotation F1: 0.626 -> 0.753Improved
predict DSL motion programs instead of binned per-frame trajectories (ablation)LAMP · Procedural dataset test, free-form camera (DSL vs trajectory)rotation MAE per axis (degrees): 8.333 -> 3.507Improved
fine-tune on DSL-converted DataDoP with regenerated captionsLAMP · DataDoP camera trajectoriesrevised F1: 0.763 -> 0.776Improved
use regenerated captions instead of original DataDoP captions in fine-tuning (ablation)LAMP · DataDoP camera trajectoriesrevised F1: 0.613 -> 0.776Improved
train from scratch on DSL-converted DataDoP instead of fine-tuning (ablation)LAMP · DataDoP camera trajectoriesrevised F1: 0.776 -> 0.776No clear effect
fine-tune on DSL-converted ET with regenerated captionsLAMP · ET dataset, mixed splitF1 score: 0.769 -> 0.779Improved
use regenerated captions instead of original ET captions in fine-tuning (ablation)LAMP · ET dataset, pure splitF1 score: 0.666 -> 0.978Improved
train on DataDoP from scratch instead of procedural data only (ablation)LAMP · ET dataset, pure splitF1 score: 0.976 -> 0.967No clear effect
replace GenDoP baseline with LAMP (no DataDoP training)LAMP · DataDoP camera trajectoriesrevised F1: 0.360 -> 0.763Improved

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