AI Paper Atlas

Research map / Video / Video segmentation and tracking

Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content

Evgeney Bogatyrev, Khaled Abud, Ivan Molodetskikh, Nikita Alutis, Dmitriy S. Vatolin

ICLR 2026 · Video › Video segmentation and tracking · approach: Real-world video super-resolution · 0 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
fine-tune on StreamSRRLFN · StreamSR test (2x)Subjective score: 2.17 -> 2.69Improved
fine-tune on StreamSRRLFN · StreamSR test (2x)PSNR: 37.03 -> 37.63Improved
fine-tune on StreamSRSPAN · StreamSR test (2x)Subjective score: 2.55 -> 3.13Improved
fine-tune on StreamSRESPCN · StreamSR test (2x)PSNR: 30.71 -> 35.76Improved
use tanh instead of ReLU activation (ablation)EfRLFN (ECA) · EfRLFN ablationSSIM: 0.847 -> 0.865Improved
use tanh instead of Sigmoid-0.5 (ablation)EfRLFN (ECA) · EfRLFN ablationSSIM: 0.856 -> 0.865Improved
use ECA instead of ESA attention (ablation)EfRLFN (tanh) · EfRLFN ablationFPS: 234 -> 314Improved
use ECA instead of ESA attention (ablation)EfRLFN (tanh) · EfRLFN ablationLPIPS: 0.171 -> 0.173Hurt
use ECA instead of ESA attention (ablation)EfRLFN (ReLU) · EfRLFN ablationSSIM: 0.849 -> 0.847Hurt
use full Charbonnier+VGG+Sobel loss instead of ablated losses (ablation)EfRLFN · StreamSR 4xSSIM: 0.865Improved
train on real LR-HR pairs instead of bicubic synthetic LR (ablation)EfRLFN · DIV2KPSNR: 33.983 -> 34.553Improved
train on real LR-HR pairs instead of bicubic synthetic LR (ablation)SPAN · DIV2KPSNR: 32.645 -> 33.511Improved

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