AI Paper Atlas

Research map / Video / Video segmentation and tracking

Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models

Claudio Rota, Marco Buzzelli, Joost van de Weijer

ECCV 2024 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 20 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
use predicted x0 (noise-free) as temporal guidance instead of x_t (ablation)StableVSR · REDS4 center cropstLP: 38.16 -> 6.16Improved
add motion compensation to the temporal guidance (ablation)StableVSR · REDS4 center cropstLP: 18.97 -> 6.16Improved
decode latent to RGB before motion compensation (ablation)StableVSR · REDS4 center cropstLP: 21.17 -> 6.16Improved
add temporal conditioning instead of single-frame sampling (ablation)StableVSR · REDS4 center cropstLP: 14.67 -> 6.16Improved
use frame-wise sampling instead of auto-regressive sampling (ablation)StableVSR · REDS4 center cropstLP: 8.61 -> 6.16Improved
add backward propagation (bidirectional) to unidirectional sampling (ablation)StableVSR · REDS4 center cropstLP: 6.36 -> 6.16Improved
use Temporal Texture Guidance via ControlNet instead of 3D conv and temporal attention video baselineSD x4 Upscaler · REDS4 center cropstLP: 13.08 -> 6.16Improved
diffusion-based generation instead of regression-based VSRStableVSR vs RVRT · REDS4PSNR: 32.74 -> 27.97Hurt
diffusion-based generation instead of regression-based VSRStableVSR vs RVRT · REDS4LPIPS: 0.128 -> 0.097Improved
increase sampling steps from 10 to 100 (ablation)StableVSR · REDS4 center cropsperceptual vs reconstructionMixed

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