AI Paper Atlas

Research map / Image generation / Super-resolution

Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images

Jinjin Gu, Haoming Cai, Chenyu Dong, Ruofan Zhang, Yulun Zhang, Wenming Yang, Chun Yuan

ECCV 2022 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution

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
increase the SRPO network from one layer to three layers (ablation)SRPO · Unreal Engine 4 test scenesedge sharpness (qualitative)Improved
deepen the SRPO network from three to seven layers (ablation)SRPO · Unreal Engine 4 test scenesedge sharpness (qualitative)No clear effect
deepen the network to 30 layers (ablation)SRPO · Unreal Engine 4 test scenesedge sharpness (qualitative)Improved
apply 8-bit static quantizationESPCN and eSR-CNN · Unreal Engine 4 test scenesvisual quality (qualitative)Hurt
apply 8-bit static quantizationSRPO · Unreal Engine 4 test scenesvisual quality (qualitative)No clear effect
predict offsets on rasterized images instead of pixels on anti-aliased images (SRPO vs eSR-CNN)SRPO · Unreal Engine 4 test scenes (x2)LPIPS: 0.1547 -> 0.1501Improved
use SRPO instead of AMD FSRSRPO · Unreal Engine 4 test scenes (x2)PSNR: 27.56 -> 26.97Hurt

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