atlas

Research map / Image generation / Image restoration

Reflection Scene Separation From a Single Image

CVPR 2020 · Image generation › Image restoration · approach: Reflection removal · 25 citations (OpenAlex)

Check 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
use the proposed separation network instead of CoRRNreflection component separation · Reflection component separation evaluation datasetLPIPS: 0.491 -> 0.194Helped
use the proposed separation network instead of Zhang et al.reflection component separation · Reflection component separation evaluation datasetSSIM: 0.854 -> 0.942Helped
use the proposed separation network instead of Zhang et al.reflection component separation · Reflection component separation evaluation datasetPSNR: 25.625 -> 35.085Helped
use the proposed enhancement network instead of CycleGANreflection scene enhancement · Reflection scene enhancement evaluation datasetLPIPS: 0.202 -> 0.151Helped
use the proposed enhancement network instead of CycleGANreflection scene enhancement · Reflection scene enhancement evaluation datasetSSIM: 0.583 -> 0.716Helped
use the proposed enhancement network instead of CycleGANreflection scene enhancement · Reflection scene enhancement evaluation datasetPSNR: 15.581 -> 16.886Helped
add a separation stage before enhancement (ablation)reflection scene enhancement · Reflection scene enhancement evaluation datasetLPIPS: 0.401 -> 0.151Helped
add a separation stage before enhancement (ablation)reflection scene enhancement · Reflection scene enhancement evaluation datasetSSIM: 0.584 -> 0.716Helped
add a separation stage before enhancement (ablation)reflection scene enhancement · Reflection scene enhancement evaluation datasetPSNR: 12.856 -> 16.886Helped
add color loss to the shift-invariant loss (ablation)reflection scene enhancement · Reflection scene enhancement evaluation datasetLPIPS: 0.198 -> 0.151Helped
add color loss to the shift-invariant loss (ablation)reflection scene enhancement · Reflection scene enhancement evaluation datasetSSIM: 0.675 -> 0.716Helped
add color loss to the shift-invariant loss (ablation)reflection scene enhancement · Reflection scene enhancement evaluation datasetPSNR: 14.875 -> 16.886Helped

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