AI Paper Atlas

Research map / Video / Video segmentation and tracking

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

Gen Li, Jie Ji, Minghai Qin, Wei Niu, Bin Ren, Fatemeh Afghah, Linke Guo, Xiaolong Ma

CVPR 2023 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 29 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
Group patches across spatial and temporal dimensions by their PSNR and overfit each group separatelyWDSR · VSD4K game-15s, ×2PSNR: 44.23 -> 45.75Improved
Group patches across spatial and temporal dimensions by their PSNR and overfit each group separatelyWDSR · VSD4K vlog-45s, ×4PSNR: 42.87 -> 43.99Improved
Train one model using only the most informative chunk instead of all spatial-temporal chunks (ablation)WDSR STDO · vlog-15s, ×2PSNR: 50.58 -> 50.42Hurt
Train one model using only the least informative chunk instead of all spatial-temporal chunks (ablation)WDSR STDO · vlog-15s, ×2PSNR: 50.58 -> 46.89Hurt
Replace separate chunk-specific models with one data-aware jointly trained model (ablation)WDSR STDO · VSD4K game-15s, ×2PSNR: 45.75 -> 45.46Hurt
Replace separate chunk-specific models with one data-aware jointly trained model (ablation)WDSR STDO · VSD4K game-15s, ×3PSNR: 40.17 -> 39.87Hurt
Replace separate chunk-specific models with one data-aware jointly trained model (ablation)WDSR STDO · VSD4K game-15s, ×4PSNR: 38.62 -> 38.14Hurt
Replace four chunk-specific models with one data-aware jointly trained model (ablation)WDSR STDO · VSD4K game-15snumber of models: 4 -> 1Improved
Increase the share of training patches from the most informative chunk (ablation)JSTDO · Video super-resolutionPSNRImproved
Vary the number of spatial-temporal chunks, with performance best around four (ablation)STDO · game-15sPSNRMixed
Apply STDO to a combined 90-second video containing scene conversions (ablation)WDSR STDO · game-45s + vlog-45s, ×4PSNR: 39.92 dB; 43.99 dB and 37.76 dBMixed

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