AI Paper Atlas

Research map / Video / Video generation

DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution

Hidir Yesiltepe, Koutilya PNVR, Gaurav Pathak, Navaneeth Bodla, Bharat Singh, Pinar Yanardag, Jinrong Xie

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 0 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 exponential-annealed decoupled time guidance instead of standard CFG (Delta=0) (ablation)DTG-Restore · GenWarp480 (heavy distortion, schedule ablation)Quality: 3.91 -> 4.58Improved
anneal Delta (exponential) instead of constant Delta=0.3 (ablation)DTG-Restore · GenWarp480 (light distortion)Quality: 4.03 -> 4.64Improved
use constant lookahead Delta=0.3 instead of Delta=0 (ablation)Std. CFG · GenWarp480 (light distortion)Quality: 4.12 -> 4.03Hurt
use exponential instead of cosine annealing (ablation)DTG-Restore · GenWarp480 (heavy distortion, schedule ablation)Quality: 4.47 -> 4.58Improved
use cosine instead of linear annealing (ablation)DTG annealing · GenWarp480 (heavy distortion, schedule ablation)Quality: 4.41 -> 4.47Improved
replace SDEdit single-point resampling (t_start=0.5) with DTG per-step decoupling (ablation)DTG-Restore · GenWarp480LAION AP: 4.38 -> 4.64Improved
replace SDEdit (t_start=0.5) with DTG (ablation)DTG-Restore · GenWarp480Warp score: 0.118 -> 0.071Improved
deeper SDEdit resampling t_start 0.3 to 0.7 (ablation)SDEdit · GenWarp480Warp score / CLIP-IQA: 0.142 -> 0.097 warp; CLIP-IQA 0.489 -> 0.478Mixed
DTG-Restore versus strongest reconstruction baseline RealViformerDTG-Restore · UDM10PSNR: 26.78 -> 25.61Hurt
DTG-Restore versus RealViformer on reference-free MANIQADTG-Restore · GenWarp480MANIQA: 0.293 -> 0.314Improved
DTG-Restore versus SeedVR2 on NIQEDTG-Restore · GenWarp480NIQE: 3.915 -> 4.337Hurt
DTG-Restore versus Venhancer in user study motion smoothnessDTG-Restore · User studyMotion Smoothness: 3.80 -> 4.52Improved

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