AI Paper Atlas

Research map / Video / Video segmentation and tracking

TurboVSR: Fantastic Video Upscalers and Where to Find Them

Zhongdao Wang, Guodongfang Zhao, Jingjing Ren, Bailan Feng, Shifeng Zhang, Wenbo Li

ICCV 2025 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 3 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 factorized first-frame conditioning instead of plain video condition (ablation)TurboVSR · SPMCSDOVER: 34.23 -> 79.15Improved
add factorized first-frame conditioning instead of plain video condition (ablation)TurboVSR · SPMCSNIQE: 6.162 -> 4.113Improved
add factorized first-frame conditioning instead of plain video condition (ablation)TurboVSR · SPMCSPSNR: 24.81 -> 22.15Hurt
add shortcut bootstrap loss to flow matching training (ablation)TurboVSR · SPMCS (4 steps)DOVER: 74.09 -> 79.15Improved
add shortcut bootstrap loss to flow matching training (ablation)TurboVSR · SPMCS (1 step)DOVER: 68.31 -> 77.08Improved
add shortcut bootstrap loss to flow matching training (ablation)TurboVSR · SPMCS (4 steps)NIQE: 4.84 -> 4.11Improved
add non-uniform timestep t sampling (with uniform d) (ablation)TurboVSR shortcut · Shortcut sampling ablation (4 steps)DOVER: 71.44 -> 78.14Improved
add non-uniform step size d sampling (with non-uniform t) (ablation)TurboVSR shortcut · Shortcut sampling ablation (4 steps)E_warp: 4.42 -> 3.57Improved
add non-uniform step size d sampling (with non-uniform t) (ablation)TurboVSR shortcut · Shortcut sampling ablation (4 steps)LPIPS: 0.218 -> 0.184Improved
reduce sampling steps from 10 to 4 (ablation)TurboVSR · SPMCSDOVER: 79.29 -> 79.15No clear effect
reduce sampling steps from 10 to 4 (ablation)TurboVSR · VSR latency (1080p)latency ms/frame: 337 -> 140Improved
reduce sampling steps from 10 to 4 (ablation)TurboVSR · UDM10MUSIQ: 59.21 -> 56.07Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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