AI Paper Atlas

Research map / Image generation / Image restoration

Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition

CVPR 2022 · Image generation › Image restoration · approach: Dehazing and deraining · 318 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
Add random scattering-coefficient sampling for self-augmentation (ablation)D4 · SOTS-indoorPSNR: 23.15 -> 25.42Helped
Add random scattering-coefficient sampling for self-augmentation (ablation)D4 · SOTS-outdoorPSNR: 24.08 -> 25.83Helped
Add pseudo scattering-coefficient and depth supervision (ablation)D4 · SOTS-indoorPSNR: 20.02 -> 25.42Helped
Add pseudo scattering-coefficient and depth supervision (ablation)D4 · SOTS-outdoorPSNR: 22.95 -> 25.83Helped
Model haze using depth and density and generate varied haze for trainingunpaired dehazing on SOTS-outdoor · SOTS-outdoorPSNR: +4.52Helped
Use D4 instead of the strongest paired baselinedehazing on SOTS-indoor · SOTS-indoorPSNR: 35.45 -> 25.42Hurt
Use D4 instead of the strongest paired baselinedehazing on I-HAZE · I-HAZEPSNR: 15.30 -> 15.61Helped

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