AI Paper Atlas

Research map / Video / Video generation

MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent

Xinyao Liao, Xianfang Zeng, Liao Wang, Gang Yu, Guosheng Lin, Chi Zhang

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 16 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 Grounded-SAM detection tool for object identification (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Object Movement Q&A: 34.33 -> 45.69Improved
add object movement control (trajectory plotting) (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Object Movement Q&A: 10.51 -> 45.69Improved
add camera motion control (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Complex Camera Motion: 0.30 -> 77.76Improved
add analytical optical flow composition (vs directly adding flows) (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Complex Camera Motion: 64.92 -> 77.76Improved
add analytical optical flow composition (vs directly adding flows) (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Object Movement Q&A: 30.07 -> 45.69Improved
fine-tune optical flow adapter on unified flow maps (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Complex Camera Motion: 48.27 -> 77.76Improved
fine-tune optical flow adapter on unified flow maps (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Object Movement Q&A: 40.56 -> 45.69Improved
use grid selection instead of direct offset generation for trajectories (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Object Movement Q&A: 29.28 -> 45.69Improved
use open-source Llama3 instead of GPT-4o as agent LLM (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Total score: 65.10 -> 63.80No clear effect
use open-source Qwen2 instead of GPT-4o as agent LLM (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Total score: 65.10 -> 61.73No clear effect
use Motion-I2V instead of SVD as base I2V model (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Total score: 65.10 -> 61.00No clear effect
add rethinking step (ablation)MotionAgent · Controllable I2V benchmark (VBench subset)Complex Camera Motion: 77.76 -> 89.04Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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