AI Paper Atlas

Research map / Image generation / Super-resolution

OSRT: Omnidirectional Image Super-Resolution With Distortion-Aware Transformer

Fanghua Yu, Xintao Wang, Mingdeng Cao, Gen Li, Ying Shan, Chao Dong

CVPR 2023 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 40 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
use distortion-aware OSRT instead of SwinIRODI-SR and SUN 360 Panorama under Fisheye downsampling, ×2 and ×4 · ODI-SR; SUN 360 PanoramaPSNR: 30.64 -> 30.77; 31.33 -> 31.52; 27.31 -> 27.41; 27.71 -> 27.84Improved
use OSRT rather than SphereSRODI-SR and SUN 360 Panorama under ERP downsampling · ODI-SR; SUN 360 Panorama ×8 and ×16WS-PSNR: 24.37 -> 24.53; 24.17 -> 24.38; 22.51 -> 22.69; 21.95 -> 22.13Improved
add DACB (ablation)OSRT-light · ODI-SR ×2; SUN360 ×2PSNR: 30.27 -> 30.41; 30.78 -> 31.00Improved
add DAAB without window condition Cw (ablation)OSRT-light · ODI-SR ×2; SUN360 ×2PSNR: 30.27 -> 30.31; 30.78 -> 30.83Improved
add window condition Cw to DAAB (ablation)OSRT-light · ODI-SR ×2; SUN360 ×2PSNR: 30.31 -> 30.32; 30.83 -> 30.84No clear effect
combine DACB and DAAB with Cw (ablation)OSRT-light · ODI-SR ×2; SUN360 ×2PSNR: 30.27 -> 30.44; 30.78 -> 31.04Improved
add DF2K-ERP pseudo-ERP data jointly (ablation)SwinIR · SUN360 ×2 and ×4PSNR: 31.21 -> 31.33; 27.39 -> 27.71Improved
add DF2K plain-image data (ablation)SwinIR · SUN360 ×2 and ×4PSNR: 31.21 -> 31.26; 27.39 -> 27.59Improved
train jointly rather than pretrain then fine-tune on DF2K-ERP and ODI-SR (ablation)SwinIR · SUN360 ×2PSNR: 31.17 -> 31.33Improved
train jointly rather than pretrain then fine-tune on DF2K-ERP and ODI-SR (ablation)SwinIR · SUN360 ×4PSNR: 27.74 -> 27.71Hurt

Later papers that compared with this method

5 later accepted papers report OSRT as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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