AI Paper Atlas

Research map / Image generation / GANs

DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning

Runsheng Yu, Wenyu Liu, Yasen Zhang, Zhi Qu, Deli Zhao, Bo Zhang

NeurIPS 2018 · Image generation › GANs · approach: GAN-based image manipulation · 71 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
DeepExposure I vs Exposure (RL baseline) with local exposuresDeepExposure · MIT-Adobe FiveK testMSE: 97.99 -> 95.44Improved
DeepExposure I vs ExposureDeepExposure · MIT-Adobe FiveK testPSNR: 28.27 -> 28.38Improved
learned RL exposure vs empirically crafted exposure fusion (FI)DeepExposure · MIT-Adobe FiveK testMSE: 105.2 -> 95.44Improved
unpaired adversarial training vs paired method DPEDDeepExposure · MIT-Adobe FiveK testPSNR: 28.20 -> 28.38Improved
use discriminator as value function (DE II) instead of separate value network (DE I) (ablation)DeepExposure · MIT-Adobe FiveK testMSE: 95.44 -> 96.42Hurt
use discriminator as value function (DE II) instead of separate value network (DE I) (ablation)DeepExposure · MIT-Adobe FiveK testPSNR: 28.38 -> 28.33Hurt
use discriminator as value function (DE II) instead of separate value network (DE I) (ablation)DeepExposure · MIT-Adobe FiveK testtraining time to converge: 320 min -> 280 minImproved

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