AI Paper Atlas

Research map / Video / Video segmentation and tracking

Stable Long-Term Recurrent Video Super-Resolution

Benjamin Naoto Chiche, Arnaud Woiselle, Joana Frontera-Pons, Jean-Luc Starck

CVPR 2022 · Video › Video segmentation and tracking · approach: Space-time video super-resolution · 34 citations (OpenAlex)

Check 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 a contractive recurrent map with unconstrained input and output networks (MRVSR) instead of three-frame feed-forward RFS3RFS3 · Quasi-Static Video Set, all reconstructed framesPSNR: +0.58 dBImproved
Use a contractive recurrent map with unconstrained input and output networks (MRVSR) instead of seven-frame RFS7RFS7 · Quasi-Static Video Set, all reconstructed framesPSNR: +0.39dBImproved
Apply soft Lipschitz constraint to all RLSP layers (ablation)RLSP · Quasi-Static Video Set, last 50 reconstructionsPSNR: -2.09dB in mean PSNRHurt
Apply hard Lipschitz constraint to all RLSP layers (ablation)RLSP · Quasi-Static Video Set, all reconstructed framesPSNR: -1.13dB in average PSNRHurt
Set MRVSR recurrent depth n_phi to 1 rather than other tested values (ablation)MRVSR · Validation setperformanceImproved

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