AI Paper Atlas

Research map / Image generation / Image restoration

Single Image Reflection Separation via Component Synergy

Qiming Hu, Xiaojie Guo

ICCV 2023 · Image generation › Image restoration · approach: Reflection removal · 65 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 learnable residue term with residual-corrected reconstruction loss (vs none) (ablation)DSRNet · SIR2 + Real20 averagePSNR: 24.84 -> 25.40Improved
use linear additive reconstruction loss instead of residual-corrected loss (ablation)DSRNet · SIR2 + Real20 averagePSNR: 25.40 -> 22.21Hurt
add feature interaction between the two streams (ablation)DSRNet · SIR2 + Real20 averagePSNR: 24.81 -> 25.40Improved
use MuGI instead of YTMT interaction (ablation)DSRNet · SIR2 + Real20 averagePSNR: 24.89 -> 25.40Improved
use DSFNet pyramid encoder instead of HyperColumn (ablation)DSRNet · SIR2 + Real20 averagePSNR: 23.99 -> 25.40Improved
add feature encoder (semantic pyramid) (ablation)DSRNet · SIR2 + Real20 averagePSNR: 24.75 -> 25.40Improved
train with extra data (Nature dataset and 13,700 synthetic pairs)DSRNet · SIR2 + Real20 averagePSNR: 25.40 -> 25.75Improved

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