AI Paper Atlas

Research map / Video / Video generation

UniVST: A Unified Framework for Training-Free Localized Video Style Transfer

Quanjian Song, Mingbao Lin, Wengyi Zhan, Shuicheng Yan, Liujuan Cao, Rongrong Ji

TPAMI 2025 · Video › Video generation · approach: Efficient video diffusion models · 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 all components to the baseline (ablation)UniVST baseline · DAVTG-WikiArt ArtFIDArtFID: 45.676 -> 37.152Improved
add localized latent blending (ablation)UniVST · DAVTG-WikiArtArtFID: 38.014 -> 37.152Improved
add AdaIN-guided latent-shift (ablation)UniVST · DAVTG-WikiArtArtFID: 37.649 -> 37.152Improved
add AdaIN-guided attention-shift (ablation)UniVST · DAVTG-WikiArtArtFID: 39.589 -> 37.152Improved
add sliding-window consistent smoothing (ablation)UniVST · DAVTG-WikiArtCLIP-F: 0.970 -> 0.980Improved
add AdaIN-guided attention-shift (ablation)UniVST · DAVTG-LaionArtFID: 32.534 -> 30.636Improved
add AdaIN-guided latent-shift (ablation)UniVST · DAVTG-Laion LPIPSLPIPS: 0.362 -> 0.383Hurt
use first frame plus previous frame anchors instead of previous frame only (ablation)point-matching mask propagation · DAVIS-Laion mask propagationAvg IoU: 0.5321 -> 0.7799Improved
use n=15 anchors instead of n=9 (ablation)point-matching mask propagation · DAVIS-Laion mask propagationAvg Dice: 0.8726 -> 0.8729; time 2.742 -> 2.878No clear effect
use k=15 in k-NN instead of k=40 (ablation)point-matching mask propagation · DAVIS-Laion mask propagationAvg Dice: 0.8719 -> 0.8772Improved
use decreasing time coefficient beta instead of increasing (ablation)AdaIN attention-shift · DAVIS-LaionArtFID: 32.158 -> 30.658Improved
use AdaIN attention-shift instead of K-V replacement (ablation)UniVST · DAVIS-LaionArtFID: 32.561 -> 30.658Improved

Earlier methods this paper compares with

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