AI Paper Atlas

Research map / Image generation / Editing and style transfer

High-Resolution Daytime Translation Without Domain Labels

Ivan Anokhin, Pavel Solovev, Denis Korzhenkov, Alexey Kharlamov, Taras Khakhulin, Aleksei Silvestrov, Sergey Nikolenko, Victor Lempitsky, Gleb Sterkin

CVPR 2020 · Image generation › Editing and style transfer · approach: Image-to-image translation · 67 citations (OpenAlex)

Check 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
Train without daytime domain labelsHiDT · Daytime landscape translationHuman preference and GAN metricsNo clear effect
Use HiDT instead of labeled baselinesDaytime translation · Hold-out datasetDIPD, CIS, and Inception score: DIPD: 0.691; CIS: 1.559; IS random: 1.673; IS swapped: 1.605Mixed
Increase the number of averaged styles from N=1 to N=10FUNIT-T · Daytime translation user studyHiDT user preference score: 0.51; 0.48; 0.47Hurt
Add the projection conditioning scheme to the discriminatorHiDT · Daytime landscape translationTranslation qualityImproved
Add auxiliary segmentation loss (ablation)HiDT · Daytime landscape translationSemantic consistencyImproved
Remove auxiliary segmentation loss (ablation)HiDT · Daytime landscape translationUser preference scoreNo clear effect
Use the autoencoding loss alone (ablation)HiDT · Hold-out dataset, swapped stylesCIS: 1.559 -> 1.179Hurt
Use the autoencoding loss alone (ablation)HiDT · Daytime style transferTarget daytime resemblanceHurt

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