AI Paper Atlas

Research map / Image generation / Image restoration

A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing

Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Wipf

ICCV 2017 · Image generation › Image restoration · approach: Dehazing and deraining · 342 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 predicted target edge from E-CNN (CEILNet vs I-CNN only) (ablation)I-CNN · L0 smoothingPSNR: 32.58 -> 37.10Improved
add predicted target edge from E-CNN (vs input edge, 64 layers) (ablation)I-CNN 64 layers · L0 smoothingPSNR: 34.86 -> 37.10Improved
use predicted target edge instead of input image edge (ablation)I-CNN 64 layers · L0 smoothingMSE: 22.50 -> 13.34Improved
stack more layers in I-CNN instead of E-CNN (64 layers vs 32 layers) (ablation)I-CNN only · L0 smoothingPSNR: 32.58 -> 33.33Improved
use 32-layer E-CNN plus 32-layer I-CNN instead of best 70-layer I-CNN (ablation)CEILNet · L0 smoothingPSNR: 33.37 -> 37.10Improved
replace Domain Transform with I-CNN given predicted edge (ablation)CEILNet · L0 smoothingPSNR: 31.17 -> 37.10Improved
use predicted edge instead of input image edge with Domain Transform (ablation)Domain Transform · L0 smoothingPSNR: 27.38 -> 31.17Improved
use CEILNet instead of Li and Brown for reflection removalCEILNet · Reflection removal (100 synthetic images)PSNR: 15.50 -> 18.55Improved
use CEILNet instead of Xu et al. for L0 smoothingCEILNet · Image smoothingPSNR: 31.66 -> 37.10Improved
use CEILNet instead of Liu et al. across four filtersCEILNet · Image smoothing vs Liu et al. [24]PSNR: 35.64 -> 39.36Improved
use CEILNet instead of Liu et al. on RGFCEILNet · Image smoothing vs Liu et al. [24]SSIM: 0.986 -> 0.989Improved
use CEILNet instead of Xu et al. for running time at 720pCEILNet · Running time 720pseconds: 0.33 -> 0.35No clear effect

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