AI Paper Atlas

Research map / Image generation / GANs

Photo-Realistic Monocular Gaze Redirection Using Generative Adversarial Networks

Zhe He, Adrian Spurr, Xucong Zhang, Otmar Hilliges

ICCV 2019 · Image generation › GANs · approach: GAN-based image manipulation · 56 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
use GAN with gaze estimation, perceptual and cycle losses instead of DeepWarpgaze redirection, easy angles · User study, correction angle [4.9, 15.0] degvote share (%): 21.9% -> 78.1%Improved
use GAN with gaze estimation, perceptual and cycle losses instead of DeepWarpgaze redirection, medium angles · User study, correction angle (15.0, 25.0] degvote share (%): 9.0% -> 91.0%Improved
use GAN with gaze estimation, perceptual and cycle losses instead of DeepWarpgaze redirection, hard angles · User study, correction angle (25.0, 35.9] degvote share (%): 13.4% -> 86.6%Improved
add the cycle reconstruction loss (ablation)gaze redirection GAN · Columbia Gaze, frontalLPIPSImproved
add the perceptual loss (ablation)gaze redirection GAN · Columbia Gaze, frontalLPIPSImproved
add the gaze estimation loss (ablation)gaze redirection GAN · Columbia Gaze, frontalgaze redirection (qualitative)Improved
add the cycle reconstruction loss or perceptual loss (ablation)gaze redirection GAN · Columbia Gaze, frontalgaze estimation errorNo clear effect
augment training set with redirected images at unseen pitch anglesVGG-16 gaze estimator · Columbia Gaze testangular error (deg): 14.3 -> 6.9Improved
augment training set with redirected images at unseen pitch anglesVGG-16 gaze estimator · MPIIGaze test (cross-dataset)angular error (deg): 20.2 -> 14.0Improved

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