AI Paper Atlas

Research map / Video / Video segmentation and tracking

Omniscient Video Super-Resolution

Peng Yi, Zhongyuan Wang, Kui Jiang, Junjun Jiang, Tao Lu, Xin Tian, Jiayi Ma

ICCV 2021 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 96 citations (OpenAlex)

Read the paper

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 hidden state from the past and LR frame from the future (hybrid vs iterative) (ablation)IVSR · 20 val sequencesPSNR: 30.66 -> 31.10Improved
add hidden states from present and future (local omniscient) (ablation)HVSR · 20 val sequencesPSNR: 31.10 -> 31.24Improved
make the framework global (bidirectional) after tuning (ablation)LOVSR 4+2 · 20 val sequencesPSNR: 31.28 -> 31.52Improved
add precursor SR output via alpha=0.01 instead of Bicubic residual (ablation)GOVSR · 20 val sequencesPSNR: 31.27 -> 31.36Improved
add precursor SR output via alpha=0.1 instead of Bicubic residual (ablation)LOVSR · 20 val sequencesPSNR: 31.24 -> 31.26Improved
raise precursor loss weight alpha from 0.1 to 1 (ablation)LOVSR · 20 val sequencesPSNR: 31.26 -> 31.17Hurt
allocate 4 blocks to precursor instead of 0 (ablation)GOVSR · 20 val sequencesPSNR: 31.20 -> 31.52Improved
allocate 4 blocks to precursor instead of 6 (6+0) (ablation)GOVSR · 20 val sequencesPSNR: 31.43 -> 31.52Improved
feed HVSR a fourth LR frame (ablation)HVSR · 20 val sequencesPSNR: 31.10 -> 31.15Improved
use LOVSR instead of HVSR with the same 4 LR framesHVSR4 · 20 val sequencesPSNR: 31.15 -> 31.28Improved
add LR frame I_{t-1} to the successor network (ablation)LOVSR 4+2 · 20 val sequencesPSNR: 31.29 -> 31.28No clear effect
add hidden state H_t of the precursor to the successor (ablation)GOVSR 4+2 Net_s · 20 val sequencesPSNR: 12.44 -> 31.52Improved

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