AI Paper Atlas

Research map / Video / Video generation

ObjCtrl-2.5D: Training-free Object Control with Camera Poses

Zhouxia Wang, Yushi Lan, Shangchen Zhou, Chen Change Loy

IJCV 2026 · Video › Video generation · approach: Trajectory-guided motion control · 25 citations (OpenAlex)

Read the paper

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 scale-wise mask dilation (ablation)ObjCtrl-2.5D · ObjCtrl-TestObjMC: 124.37 -> 120.37Improved
add Shared Warping Latent (ablation)ObjCtrl-2.5D · ObjCtrl-TestObjMC: 122.07 -> 120.37Improved
replace FreeTraj copy-pasting shared latent with SWL (ablation)ObjCtrl-2.5D · ObjCtrl-TestObjMC: 138.22 -> 120.37Improved
replace copy-pasting with SWL (ablation)ObjCtrl-2.5D · ObjCtrl-TestFID: 248.39 -> 247.48No clear effect
add Layer Control Module (ablation)CameraCtrl-SVD · qualitativeobject motion controlImproved
use 2D trajectory with depth from conditional image instead of real 3D trajectory (ablation)ObjCtrl-2.5D · DAVISObjMC: 92.08 -> 91.42No clear effect
replace training-free PEEKABOO* with ObjCtrl-2.5DPEEKABOO* · DAVISObjMC: 128.05 -> 91.42Improved
replace training-free FreeTraj* with ObjCtrl-2.5DFreeTraj* · ObjCtrl-TestObjMC: 158.39 -> 120.37Improved
replace training-based DragNUWA with ObjCtrl-2.5DDragNUWA · DAVISObjMC: 37.57 -> 91.42Hurt
replace training-based DragAnything with ObjCtrl-2.5DDragAnything · ObjCtrl-TestDynamic Degree: 0.7436 -> 0.3461Hurt
replace PEEKABOO* with ObjCtrl-2.5DPEEKABOO* · DAVISDynamic Degree: 0.2472 -> 0.3483Improved

Later papers that compared with this method

1 later accepted paper reports ObjCtrl-2.5D as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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