AI Paper Atlas

Research map / Detection and segmentation / CNN features

AOD-Net: All-In-One Dehazing Network

Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng

ICCV 2017 · Detection and segmentation › CNN features · approach: Context for hard detection conditions · 2,674 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 concatenation (multi-scale skip) layers to the K-estimation module (ablation)AOD-Net · NYU2 TestSet A (3,170 synthetic images)PSNR (dB): 19.0674 -> 19.6954Improved
add concatenation layers to the K-estimation module (ablation)AOD-Net · NYU2 TestSet A (3,170 synthetic images)SSIM: 0.7707 -> 0.8478Improved
jointly estimate 1/t(x) and A in one K(x) instead of learning t(x) with A from DCP (ablation)AOD-Net · Challenging Real Photos (qualitative)visual qualityImproved
append AOD-Net before Faster R-CNNFaster R-CNN · Pascal VOC 2007 synthetic haze, Heavy hazemAP: 0.5155 -> 0.5794Improved
append AOD-Net before Faster R-CNNFaster R-CNN · Pascal VOC 2007 synthetic haze, Medium hazemAP: 0.6046 -> 0.6401Improved
append AOD-Net before Faster R-CNNFaster R-CNN · Pascal VOC 2007 synthetic haze, Light hazemAP: 0.6410 -> 0.6701Improved
jointly tune AOD-Net and Faster R-CNN end to endAOD-Net + Faster R-CNN · Pascal VOC 2007 synthetic haze, Heavy hazemAP: 0.5794 -> 0.6819Improved
use AOD-Net instead of DehazeNet as dehazing front endFaster R-CNN · Natural hazy images (qualitative)detection qualityImproved
add heavy haze to imagesFaster R-CNN · Pascal VOC 2007 synthetic hazemAP: 0.6990 -> 0.5155Hurt
use ReLU instead of BReLU (ablation)AOD-Net · Synthetic dehazingperformanceImproved
use AOD-Net instead of DCP on MiddleburyDehazing · Middlebury TestSet B (800 synthetic images)PSNR (dB): 18.9781 -> 21.5412Improved

Later papers that compared with this method

1 later accepted paper reports AODNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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