AI Paper Atlas

Research map / Image generation / Super-resolution

LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation

Ruizhi Shao, Gaochang Wu, Yuemei Zhou, Ying Fu, Lu Fang, Yebin Liu

ICCV 2021 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 64 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
replace feature-based/deep baselines with LocalTrans local transformercross-resolution homography estimation · MS-COCO 4x gapPSNR: 27.89 -> 30.17Improved
replace MHN with LocalTranscross-resolution homography estimation · MS-COCO 8x gapPSNR: 20.24 -> 24.12Improved
replace MHN with LocalTranscross-resolution homography estimation · MS-COCO 8x gapSSIM: 0.860 -> 0.930Improved
use local attention kernel instead of global attention (1 scale) (ablation)multiscale transformer · 128x128 input, 1 scalespeed: 152fps -> 249fpsImproved
use local attention kernel instead of global attention (3 scales) (ablation)multiscale transformer · 128x128 input, 3 scalesspeed: 16.4fps -> 132fpsImproved
use local attention kernel instead of global attention (3 scales) (ablation)multiscale transformer · 128x128 input, 3 scalesGPU memory: 476.9M -> 67.7MImproved
use local attention kernel instead of global attention (3 scales) (ablation)multiscale transformer · 256x256 input, 3 scalesspeed: 4.31fps -> 87.7fpsImproved
use local attention kernel instead of global attention (3 scales) (ablation)multiscale transformer · 256x256 input, 3 scalesGPU memory: 2434M -> 287.0MImproved
use local attention kernel instead of global attention (1 scale) (ablation)multiscale transformer · 256x256 input, 1 scaleGPU memory: 208.4M -> 196.9MNo clear effect
use multiscale local transformer instead of single-scale global transformer (ablation)LocalTrans · cross-resolution homographyaccuracyImproved

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