AI Paper Atlas

Research map / Image generation / Super-resolution

LAR-SR: A Local Autoregressive Model for Image Super-Resolution

Baisong Guo, Xiaoyun Zhang, Haoning Wu, Yu Wang, Ya Zhang, Yan-Feng Wang

CVPR 2022 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 32 citations (OpenAlex)

Check 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 local autoregressive texture generation with a learned texture codebookLAR-SR · DIV2K validation ×4LPIPS: 0.121 -> 0.114Improved
Use local autoregressive texture generation with a learned texture codebookLAR-SR · DIV2K validation ×4LPIPS: 0.110 -> 0.114Hurt
Use local autoregressive texture generation with a learned texture codebookLAR-SR · CelebA test ×8LPIPS: 0.085 -> 0.077Improved
Use local autoregressive texture generation with a learned texture codebookLAR-SR · FFHQ test ×8LPIPS: 0.100 -> 0.088Improved
Replace LAR layers with local mask attention (ablation)LAR-SR · DIV2K validation ×4Time: 14.7s -> 7.8sImproved
Replace LAR layers with local mask attention (ablation)LAR-SR · DIV2K validation ×4LPIPS: 0.114 -> 0.118Hurt
Set patch size to 1×1 rather than the 4×4 configuration (ablation)LAR-SR · DIV2K validation ×4LPIPS: 0.114 -> 0.163Hurt
Set patch size to 2×2 rather than the 4×4 configuration (ablation)LAR-SR · DIV2K validation ×4LPIPS: 0.114 -> 0.120Hurt
Set patch size to 3×3 rather than the 4×4 configuration (ablation)LAR-SR · DIV2K validation ×4LPIPS: 0.114 -> 0.116Hurt
Add a coarse-SR structural branch in Stage 1 and condition Stage 2 on coarse SR (ablation)LAR-SR · DIV2K validation ×4LPIPS: 0.185 -> 0.114Improved
Add the coarse-SR structural input to the Stage 1 decoder (ablation)LAR-SR · DIV2K validation ×4LPIPS: 0.164 -> 0.114Improved
Use LAR-SR instead of VQVAE+pixelCNNCelebA ×8 · CelebA ×8Time: 230.7s -> 1.2sImproved

Later papers that compared with this method

1 later accepted paper reports LAR-SR as a baseline in their results tables; 1 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