AI Paper Atlas

Research map / Video / Video segmentation and tracking

Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features

Liying Yang, Chen Liu, Zhenwei Zhu, Ajian Liu, Hui Ma, Jian Nong, Yanyan Liang

ICCV 2025 · Video › Video segmentation and tracking · approach: Video restoration with temporal priors · 8 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 point initialization from a large reconstruction model (ablation)baseline · Consistent4D datasetFVD: 953.6300 -> 913.371Improved
add LPIPS loss (ablation)model B · Consistent4D datasetFVD: 913.371 -> 899.5714Improved
add frame features without decoupling (ablation)model C · Consistent4D datasetFVD: 899.5714 -> 888.6579Improved
add DSFD dynamic-static decoupling (ablation)model D · Consistent4D datasetFVD: 888.6579 -> 861.6075Improved
add DSFD dynamic-static decoupling (ablation)model D · Objaverse datasetFVD: 1005.7503 -> 989.0834Improved
add TSSF with average pooling (ablation)model E (DSFD) · Consistent4D datasetFVD: 861.6075 -> 839.6600Improved
replace average pooling with adaptive global-awareness fusion (TSSF-GA) (ablation)model F · Consistent4D datasetFVD: 839.6600 -> 799.9367Improved
use distance-awareness fusion (TSSF-DA) instead of GA (ablation)DS4D-GA · Consistent4D datasetFVD: 799.9367 -> 784.0235Improved
use distance-awareness fusion (TSSF-DA) instead of GA (ablation)DS4D-GA · Objaverse datasetFVD: 890.2646 -> 870.9489Improved
add point initialization (ablation)baseline · Objaverse datasetFVD: 1072.1292 -> 1062.9398Improved
replace STAG4D with DS4D-DA decoupling methodSTAG4D · Consistent4D datasetFVD: 986.8271 -> 784.0235Improved
replace STAG4D with DS4D-DA on low-quality inputsSTAG4D · Consistent4D (low-quality input images)FVD: 1311.8770 -> 805.4721Improved

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