AI Paper Atlas

Research map / Image generation / Image restoration

Proximal Dehaze-Net: A Prior Learning-Based Deep Network for Single Image Dehazing

Dong Yang, Jian Sun

ECCV 2018 · Image generation › Image restoration · approach: Dehazing and deraining · 323 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 learned transmission prior (ablation)Net-S1 (one-stage dehaze-net) · TestBPSNR: 19.50 -> 20.14Improved
add learned dark channel prior (ablation)Net-S1 (one-stage dehaze-net) · TestBPSNR: 15.42 -> 20.14Improved
replace hand-set energy L1 prior with learned priors in network (ablation)Ener-L1 · TestBPSNR: 16.97 -> 20.14Improved
add a second stage (ablation)Net-S1 · TestBPSNR: 20.14 -> 21.02Improved
use 7x7 kernels (ablation)Net-S1 · TestBPSNR: 20.14 -> 21.24Improved
use 64 filters per layer instead of 9 (ablation)Net-S1 · TestBPSNR: 20.14 -> 21.20Improved
increase network complexity (two stages) (ablation)Net-S1 · TestBrunning time and visual quality: 0.058s -> 0.096sMixed
use 64 filters per layer (ablation)Net-S1 · TestBrunning time: 0.058s -> 0.143sHurt

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