AI Paper Atlas

Research map / Video / Video generation

MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation

Yanchen Liu, Yanan Sun, Zhening Xing, Junyao Gao, Kai Chen, Wenjie Pei

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 5 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
use MotionShot instead of MotionCloneMotionShot · Motion transfer, 40 reference videosCLIP text alignment: 26.41 -> 26.95Improved
use MotionShot instead of MotionCloneMotionShot · Motion transfer, 40 reference videosCLIP temporal consistency: 97.48 -> 97.81Improved
use MotionShot instead of MotionCloneMotionShot · Motion transfer, 40 reference videosuser study motion preservation: 2.90 -> 4.95Improved
use MotionShot instead of MotionCloneMotionShot · Motion transfer, 40 reference videosuser study appearance diversity: 2.50 -> 4.95Improved
use MotionShot instead of Tune-A-VideoMotionShot · Motion transfer, 40 reference videosuser study text alignment: 2.88 -> 4.94Improved
use MotionShot instead of Control-A-VideoMotionShot · Motion transfer, 40 reference videosuser study temporal consistency: 2.92 -> 4.90Improved
fuse SD and DINO features for keypoint matching instead of either alone or X-Pose detector (ablation)MotionShot · Motion transfer, 40 reference videosqualitative motion alignmentImproved
use TPS-based keypoint shape retargeting instead of original or resized reference sequences (ablation)MotionShot · Motion transfer, 40 reference videosqualitative motion-shape alignmentImproved
use m=30 sampled keypoints instead of m=10 (ablation)MotionShot · Motion transfer, 40 reference videosqualitative TPS deformationImproved
use m=30 sampled keypoints instead of m=60 (ablation)MotionShot · Motion transfer, 40 reference videosqualitative TPS deformationImproved
add fake target object generation conditioned on a degraded reference first-frame segmentationMotionShot · Motion transfer, 40 reference videosmotion transfer stabilityImproved
use point-based target keypoint guidance instead of TPS-warped framesMotionShot · Motion transfer, 40 reference videostemporal attention guidanceHurt

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