AI Paper Atlas

Research map / Image generation / Super-resolution

Local Implicit Normalizing Flow for Arbitrary-Scale Image Super-Resolution

Jie-En Yao, Li-Yuan Tsao, Yi-Chen Lo, Roy Tseng, Chia-Che Chang, Chun-Yi Lee

CVPR 2023 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 48 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 LINF with random sampling at τ=0.8RRDB-based ×4 super-resolution · DIV2K validationLPIPS: 0.112 vs 0.136Improved
Use LINF with random sampling at τ=0.8RRDB-based ×4 super-resolution · DIV2K validationPSNR: 27.33 vs 27.41Mixed
Use Fourier feature ensemble instead of local ensemble (ablation)LINF · DIV2K validation, ×4 SRtime (s): 2.16 -> 1.44Improved
Use Fourier feature ensemble instead of local ensemble (ablation)LINF · DIV2K validation, ×4 SRPSNR: 29.04 -> 29.04No clear effect
Add amplitude scaling by ensemble weights (ablation)LINF Fourier feature ensemble · DIV2K validation, ×4 SRLPIPS: 0.271 -> 0.270Improved
Use 3×3 patches instead of pixel-wise modeling (ablation)LINF · DIV2K validation, ×4 SR, τ=0.6LPIPS: 0.270 -> 0.158Improved
Use 3×3 patches instead of pixel-wise modeling (ablation)LINF · DIV2K validation, ×4 SR, τ=0PSNR: 29.04 -> 28.85Hurt
Increase sampling temperature from deterministic to random samplingLINF · DIV2K validation, ×4 SRLPIPS: 0.248 -> 0.112Mixed

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