AI Paper Atlas

Research map / Image generation / Super-resolution

LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction

Kai XU, Zhikang Zhang, Fengbo Ren

ECCV 2018 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 60 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 progressive Laplacian-pyramid reconstruction instead of single-step generation (CSGM)LAPRAN · Set5 (CR=5)PSNR (dB): 27.31 -> 34.79Improved
use progressive Laplacian-pyramid reconstruction instead of single-step generation (CSGM)LAPRAN · Set14 (CR=30)PSNR (dB): 23.97 -> 27.09Improved
raise compression ratio from 5 to 30LAPRAN · MNISTPSNR (dB): 38.46 -> 31.28Hurt
raise compression ratio from 5 to 30D-AMP · CIFAR10PSNR (dB): 41.35 -> 10.62Hurt
raise compression ratio from 5 to 30LAPRAN · Set5PSNR (dB): 34.79 -> 28.61Hurt
raise compression ratio from 5 to 30ReconNet · Set5PSNR (dB): 31.78 -> 25.60Hurt
use LAPRAN instead of ReconNetLAPRAN · Set14 (CR=20)PSNR (dB): 25.38 -> 28.39Improved
use LAPRAN instead of ReconNetLAPRAN · runtime, 64x64 patch (CR=5)runtime (s): 2.005e-3 -> 6.241e-3Hurt
use LAPRAN instead of CSGMLAPRAN · runtime, 64x64 patch (CR=5)runtime (s): 1.448e-1 -> 6.241e-3Improved
use LAPRAN instead of TVAL3LAPRAN · runtime, 64x64 patch (CR=5)runtime (s): 1.858e1 -> 6.241e-3Improved
use LAPRAN instead of LDAMPLAPRAN · CIFAR10 (CR=10)SSIM: 0.899 -> 0.943Improved
initialize each stage with weights of previous stage (weight transfer)LAPRAN · trainingstability/convergenceImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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