AI Paper Atlas

Research map / Image generation / Super-resolution

Journey Towards Tiny Perceptual Super-Resolution

Royson Lee, Łukasz Dudziak, Mohamed Abdelfattah, Stylianos I. Venieris, Hyeji Kim, Hongkai Wen, Nicholas D. Lane

ECCV 2020 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 58 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
compare TPSR-D2 (searched discriminator, tiny generator) against SRGANTPSR x4 · Set5LPIPS: 0.0878 -> 0.076Improved
compare TPSR-D2 against EnhanceNetTPSR x4 · Set5LPIPS: 0.1039 -> 0.076Improved
compare TPSR-D2 against EnhanceNet on PSNRTPSR x4 · Set5PSNR: 28.51 -> 29.60Improved
compare TPSR-D2 against ESRGANTPSR x4 · Set5LPIPS: 0.076 -> 0.0745Hurt
compare TPSR-D2 against FEQE on distortionTPSR x4 · Set5PSNR: 29.60 -> 31.29Hurt
compare TPSR-D2 against FEQE on perceptual metricTPSR x4 · Set5LPIPS: 0.0912 -> 0.076Improved
use NAS-searched discriminators (D1, D2, D3) instead of SRGAN, ESRGAN and JAGAN discriminators (ablation)TPSR generator · weighted average of test benchmarksLPIPSImproved
search discriminator with LPIPS reward instead of no-reference NIQE/PI (ablation)discriminator search · DIV2K proxy tasksearch stabilityImproved
initialize final generator training with shared weight cache (ablation)TPSR generator · DIV2KPSNRImproved

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