AI Paper Atlas

Research map / Video / Video generation

DIVER: Disentangling Camera–Object and Active–Passive Motion for Video Generation

Shaowei Liu, Xuanchi Ren, Tianchang Shen, Huan Ling, Saurabh Gupta, Shenlong Wang, Sanja Fidler, Jun Gao

ECCV 2026 · Video › Video generation · approach: Trajectory-guided motion control

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 canonical fixed-view branch (dual-stream) (ablation)MoRight · CookingEPE: 14.30 -> 4.27Improved
add canonical fixed-view branch (dual-stream) (ablation)MoRight · CookingFID: 51.17 -> 39.94Improved
add active/passive motion decomposition (ablation)MoRight · CookingFID: 44.04 -> 39.94Improved
add active/passive motion decomposition (ablation)MoRight · CookingFVD: 784.19 -> 730.46Improved
single-pass dual-stream instead of cascaded static-camera plus camera control (ablation)MoRight · Cookingtranslation error: 11.50 -> 10.11Improved
add mixed supervision with single-view real data (ablation)MoRight · Cookingrotation error: 2.22 -> 2.16Improved
add mixed supervision with single-view real data (ablation)MoRight · CookingFVD: 808.96 -> 730.46Improved
use coarse segment-level trajectories instead of pixel tracks (ablation)MoRight · CookingFID: 39.83 vs 39.94No clear effect
use passive motion input instead of active (ablation)MoRight · CookingEPE: 4.27 -> 7.27Mixed
MoRight with first-frame trajectories vs WanMove with privileged tracksMoRight · DynPose-100KPSNR: 13.91 -> 12.30Hurt
MoRight vs WanMove on EPEMoRight · DynPose-100KEPE: 8.05 -> 7.64Mixed
MoRight vs baselines with only active motion descriptionMoRight · WISAFID: 57.29 -> 52.95Improved

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