AI Paper Atlas

Research map / Video / Video segmentation and tracking

Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning

Liad Pollak Zuckerman, Eyal Naor, George Pisha, Shai Bagon, Michal Irani

ECCV 2020 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 6 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 across-dimension examples instead of within-dimension examples only (ablation)Deep internal TSR network · TSR x2 coarse scalePSNR [dB]: 33.96 -> 34.25Improved
use across-dimension examples instead of within-dimension examples only (ablation)Deep internal TSR network · TSR x2 coarse scaleLPIPS: 0.035 -> 0.033Improved
select the best training configuration per video (ablation)Deep internal TSR network · TSR x2 coarse scalePSNR [dB]: 33.96 -> 34.33Improved
select the best training configuration per video (ablation)Deep internal TSR network · TSR x2 coarse scaleSSIM: 0.962 -> 0.965Improved
use unsupervised internal training instead of supervised FlawlessDeep internal TSR network · Challenging videosPSNR [dB]: 27.58 -> 28.58Improved
use unsupervised internal training instead of supervised FlawlessDeep internal TSR network · Entire datasetPSNR [dB]: 28.22 -> 28.63Improved
use unsupervised internal training instead of supervised FlawlessDeep internal TSR network · Entire datasetSSIM: 0.918 -> 0.917No clear effect
use dedicated TSR instead of frame interpolation (DAIN)Deep internal TSR network · Entire datasetPSNR [dB]: 27.29 -> 28.63Improved
use sophisticated frame interpolation (DAIN) instead of linear interpolationDeep internal TSR network · Challenging videosPSNR [dB]: 26.99 -> 27.09No clear effect

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