AI Paper Atlas

Research map / Image generation / Super-resolution

Lightweight Image Super-Resolution with Superpixel Token Interaction

Aiping Zhang, Wenqi Ren, Yi Liu, Xiaochun Cao

ICCV 2023 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 79 citations (OpenAlex)

Read the paper

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
combine SPCA with ISPA instead of using ISPA alone (ablation)SPIN · Urban100 x4PSNR (dB): 26.30 -> 26.55Improved
combine ISPA with SPCA instead of using SPCA alone (ablation)SPIN · Urban100 x4PSNR (dB): 26.34 -> 26.55Improved
interleave ISPA and SPCA sequentially instead of in parallel (ablation)SPIN · Urban100 x4PSNR (dB): 26.52 -> 26.55Improved
restrict superpixel association to neighboring pixels instead of soft vector quantization (ablation)SPIN · Urban100 x4PSNR (dB): 26.28 -> 26.55Improved
use superpixel regions instead of regular patch partition (ablation)SPIN · Manga109 x4PSNR (dB): 30.70 -> 30.98Improved
increase number of SPI blocks beyond 8SPIN · Set5 x4PSNR (dB)Hurt
increase number of SPI blocks from 4 to 8SPIN · Set5 x4PSNR (dB)Improved

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