AI Paper Atlas

Research map / Image generation / GANs

HardGAN: A Haze-Aware Representation Distillation GAN for Single Image Dehazing

Qili Deng, Ziling Huang, Chung-Chi Tsai, Chia-Wen Lin

ECCV 2020 · Image generation › GANs · approach: GAN-based image manipulation · 122 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 local spatial structure preservation (L) (ablation)HardGAN baseline · SOTS OutdoorPSNR: 30.78 -> 33.54Improved
add local spatial structure preservation (L) (ablation)HardGAN baseline · SOTS IndoorPSNR: 32.25 -> 35.20Improved
add global atmospheric brightness control (G) (ablation)HardGAN baseline · SOTS OutdoorPSNR: 30.78 -> 33.77Improved
add global atmospheric brightness control (G) (ablation)HardGAN baseline · SOTS IndoorPSNR: 32.25 -> 35.48Improved
add global brightness control (G) on top of local preservation (ablation)HardGAN with L · SOTS OutdoorPSNR: 33.54 -> 34.34Improved
add local preservation (L) on top of global control (ablation)HardGAN with G · SOTS IndoorPSNR: 35.48 -> 36.56Improved
add both L and G (ablation)HardGAN baseline · SOTS OutdoorLPIPS: 0.025 -> 0.010Improved
add both L and G (ablation)HardGAN baseline · SOTS IndoorSSIM: 0.9838 -> 0.9905Improved
add local preservation (L) (ablation)HardGAN baseline · SOTS IndoorLPIPS: 0.220 -> 0.222No clear effect
use HardGAN instead of FFANetFFANet · SOTS IndoorPSNR: 36.39 -> 36.56Improved
use HardGAN instead of FFANetFFANet · SOTS OutdoorPSNR: 33.57 -> 34.34Improved
use HardGAN instead of best challenge entryECNU-Trident · NH-HAZEPSNR: 21.41 -> 21.70Improved

Later papers that compared with this method

1 later accepted paper reports HardGAN 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