atlas

Research map / Image generation / Image restoration

Single Image Reflection Separation With Perceptual Losses

CVPR 2018 · Image generation › Image restoration · approach: Dehazing and deraining · 398 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 feature loss (ablation)Ours · CEILNet syntheticPSNR: 18.24 -> 22.63Helped
Add feature loss (ablation)Ours · Real test setPSNR: 19.07 -> 21.30Helped
Add adversarial loss (ablation)Ours · CEILNet syntheticPSNR: 20.80 -> 22.63Helped
Add adversarial loss (ablation)Ours · Real test setPSNR: 21.12 -> 21.30Helped
Add exclusion loss (ablation)Ours · CEILNet syntheticPSNR: 19.58 -> 22.63Helped
Add exclusion loss (ablation)Ours · Real test setPSNR: 20.22 -> 21.30Helped
Use feature, adversarial, and exclusion losses instead of adversarial loss alone (ablation)Ours · CEILNet syntheticPSNR: 18.05 -> 22.63Helped
Use feature, adversarial, and exclusion losses instead of adversarial loss alone (ablation)Ours · Real test setPSNR: 19.52 -> 21.30Helped
Use Ours rather than CEILNetReflection separation · User study comparisonsPreference rate: 84.2%Helped
Use Ours rather than Li and BrownReflection separation · User study comparisonsPreference rate: 87.8%Helped

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