AI Paper Atlas

Research map / Video / Video generation

MoonShot: Towards Controllable Video Generation and Editing with Motion-Aware Multimodal Conditions

David Junhao Zhang, Dongxu Li, Hung Le, Mike Zheng Shou, Caiming Xiong, Doyen Sahoo

IJCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 67 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
add image condition (multimodal conditioning) to text-only (ablation)MoonShot video model · MSR-VTT, 16 framesFVD: 602 -> 542Improved
add image condition (multimodal conditioning) to text-only (ablation)MoonShot video model · MSR-VTT, 8 framesFVD: 576 -> 539No clear effect
add image condition (multimodal conditioning) to text-only (ablation)MoonShot video model · MSR-VTT, 16 framestext-video alignment preference: 8% -> 92%Improved
add image condition (multimodal conditioning) to text-only (ablation)MoonShot video model · MSR-VTT, 16 framesquality preference: 3% -> 97%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