AI Paper Atlas

Research map / Image generation / Super-resolution

LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block

Xiaotong Luo, Yuan Xie, Yulun Zhang, Yanyun Qu, Cuihua Li, Yun Fu

ECCV 2020 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 377 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
add lattice block to baseline (ablation)LatticeNet baseline · Set5 2x SRPSNR: 37.84 -> 37.96Improved
add lattice block to baseline (ablation)LatticeNet baseline · Set14 2x SRPSNR: 33.43 -> 33.59Improved
add backward fusion module to baseline (ablation)LatticeNet baseline · Set5 2x SRPSNR: 37.84 -> 37.88Improved
add backward fusion module to baseline (ablation)LatticeNet baseline · Set14 2x SRPSNR: 33.43 -> 33.47Improved
use BFM instead of 1x1 conv fusion (ablation)LatticeNet baseline · Set5 2x SRPSNR: 37.85 -> 37.88Improved
combine LB and BFM (ablation)LatticeNet baseline · Set5 2x SRPSNR: 37.84 -> 38.01Improved
combine mean pooling and std pooling for combination coefficients (vs MP only) (ablation)LatticeNet · Set5 2x SRPSNR: 37.985 -> 38.012Improved
combine mean pooling and std pooling (vs SDP only) (ablation)LatticeNet · Urban100 2x SRPSNR: 32.099 -> 32.145Improved
replace four residual blocks with lattice blocks in SRResNet (ablation)SRResNet · Set5 4x SRPSNR: 32.18 -> 32.20No clear effect
replace residual blocks with lattice blocks in RCAN (ablation)RCAN · Set5 4x SRPSNR: 32.63 -> 32.59No clear effect
increase number of lattice blocks from 2 to 10 (ablation)LatticeNet · Set5 4x SRPSNR: 32.03 -> 32.35Improved
increase number of lattice blocks from 4 to 8 (ablation)LatticeNet · Set5 4x SRPSNR: 32.18 -> 32.29Improved

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