AI Paper Atlas

Research map / Video / Video generation

FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control

Zhiyuan Zhang, Can Wang, Dongdong Chen, Jing Liao

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
use sequence-concatenation conditioning instead of ControlNet-style injection (ablation)FlexTraj · DAVIS alignedTrajErr: 0.131 -> 0.024Improved
use sequence-concatenation conditioning instead of ControlNet-style injection (ablation)FlexTraj · DAVIS unalignedTrajSIM: 0.556 -> 0.908Improved
use density/alignment annealing curriculum instead of random task mixing (ablation)FlexTraj · DAVIS alignedTrajErr: 0.126 -> 0.024Improved
use density/alignment annealing curriculum instead of random task mixing (ablation)FlexTraj · DAVIS alignedFVD: 1034.6 -> 693.3Improved
add trajectory ID to point representation (ablation)FlexTraj · DAVIS alignedTrajErr: 0.029 -> 0.024Improved
add trajectory ID to point representation (ablation)FlexTraj · DAVIS alignedFVD: 668.2 -> 693.3No clear effect
add segmentation ID to point representation (ablation)FlexTraj · DAVIS alignedTrajErr: 0.040 -> 0.024Improved
add segmentation ID to point representation (ablation)FlexTraj · DAVIS alignedFVD: 707.9 -> 693.3No clear effect
use trained point trajectory model with sparse input instead of densifying with templates (Sparse2Dense) (ablation)FlexTraj · DAVIS alignedTrajErr: 0.126 -> 0.024Improved
use FlexTraj over best baseline for dense controlFlexTraj · DAVIS denseFVD: 705.3 -> 532.4Improved
use FlexTraj over DAS for dense controlFlexTraj · FlexBench denseFVD: 1338.8 -> 1397.8Hurt
use FlexTraj with Wan2.2 5B vs Wan-Move 14BFlexTraj · MoveBenchPSNR/EPE: 17.8 -> 17.4 PSNR; 2.6 -> 2.7 EPENo clear effect

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