AI Paper Atlas

Research map / Video / Video generation

Temporal-Consistent Video Restoration with Pre-trained Diffusion Models

Hengkang Wang, Yang Liu, Huidong Liu, Chien-Chih Wang, Yanhui Guo, Hongdong Li, Bryan Wang, Ju Sun

AAAI 2026 · Video › Video generation · approach: Diffusion-based video editing · 4 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 shared-seed noise prior with small per-frame residuals (ablation)seed-space MAP baseline · DAVIS video super-resolution x4WE (x10^-2): 1.398 -> 1.057; PSNR 24.70 -> 26.09Improved
add progressive warping with optical flow refinement (ablation)seed-space MAP baseline · DAVIS video super-resolution x4WE (x10^-2): 1.398 -> 0.943; PSNR 24.70 -> 27.14Improved
combine noise prior and progressive warping (ablation)seed-space MAP baseline · DAVIS video super-resolution x4PSNR: 24.70 -> 27.95; WE 1.398 -> 0.725Improved
use 4 DDIM reverse steps instead of 2 (ablation)Ours · DAVIS video super-resolution x4PSNR: 27.87 -> 27.95Improved
increase DDIM reverse steps from 4 to 10 (ablation)Ours · DAVIS video super-resolution x4PSNR: 27.95 -> 27.70Hurt
restrict residual ball radius to 0.1 (ablation)Ours · DAVIS video super-resolution x4PSNR: 27.95 -> 25.74Hurt
increase residual ball radius from 1.0 to 10.0 (ablation)Ours · DAVIS video super-resolution x4PSNR: 27.95 -> 27.91No clear effect
raise residual learning rate to 0.01 (ablation)Ours · DAVIS video super-resolution x4PSNR: 27.95 -> 27.19Hurt
lower residual learning rate to 0.0001 (ablation)Ours · DAVIS video super-resolution x4PSNR: 27.95 -> 26.17Hurt
replace CG-based zero-shot methods with seed-space MAP framework on motion deblurringvideo restoration · DAVIS temporal deconvolution with spatial deblurringPSNR: 15.94 -> 26.97Improved

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