AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-Supervised Deep Blind Video Super-Resolution

Haoran Bai, Jinshan Pan

TPAMI 2024 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 32 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
add both self-supervised constraints (ablation)self-supervised blind video SR · REDS4PSNR: 25.73 -> 29.23Improved
add kernel-related constraint (ablation)self-supervised blind video SR · REDS4PSNR: 27.66 -> 29.23Improved
add auxiliary supervised constraint (ablation)self-supervised blind video SR · SPMCSPSNR: 25.67 -> 27.77Improved
add detach so the constraint only updates kernel network (ablation)self-supervised blind video SR · VID4PSNR: 23.03 -> 24.59Improved
add temporal information (warped auxiliary frames) to the constraint (ablation)self-supervised blind video SR · REDS4PSNR: 28.40 -> 29.23Improved
add temporal information (ablation)self-supervised blind video SR · REDS4SSIM: 0.8248 -> 0.8453Improved
add both constraints, effect on kernel quality (ablation)self-supervised blind video SR · REDS4 regenerated LRPSNR: 30.49 -> 39.62Improved
online self-supervised fine-tuning on real videos (ablation)self-supervised blind video SR · real videosNIQE: 13.357 -> 12.483Improved
use HR videos as supervision instead of self-supervision (ablation)self-supervised blind video SR · SPMCSPSNR: 27.77 -> 27.99No clear effect
self-supervised method vs supervised EDVR on Gaussian-blur REDS4EDVR · REDS4PSNR: 27.91 -> 29.23Improved
add explicit blur kernel estimation vs blind image SR methodsIKC · benchmarksPSNR: 1.06dBImproved

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