AI Paper Atlas

Research map / Image generation / Editing and style transfer

DRIT++: Diverse Image-to-Image Translation via Disentangled Representations

Hsin-Ying Lee, Hung-Yu Tseng, Qi Mao, Jia‐Bin Huang, Yu-Ding Lu, Maneesh Singh, Ming–Hsuan Yang

IJCV 2020 · Image generation › Editing and style transfer · approach: Image-to-image translation · 529 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 content discriminator (ablation)DRIT · Yosemite winter to summerFID: 46.92 -> 41.34Improved
add latent regression loss (ablation)DRIT · Yosemite winter to summerFID: 53.12 -> 41.34Improved
add latent regression loss (ablation)DRIT · Yosemite winter to summerLPIPS: 0.0158 -> 0.0965Improved
add KL loss (ablation)DRIT · Yosemite winter to summerFID: 40.08 -> 41.34Hurt
add mode-seeking regularization (DRIT++)DRIT · Yosemite winter to summerLPIPS: 0.0965 -> 0.1183Improved
add mode-seeking regularization (DRIT++)DRIT · Cat to DogLPIPS: 0.245 -> 0.280Improved
add mode-seeking regularization (DRIT++)DRIT · Cat to DogFID: 24.306 -> 17.253Improved
add content discriminator (ablation)DRIT++ · cat2dogcontent distance: 55.45 -> 10.45Improved
add content discriminator (ablation)DRIT++ · Yosemitecontent distance: 58.69 -> 31.56Improved
use multi-domain model instead of two-domainDRIT++ · Yosemite winter to summerFID: 41.02 -> 44.86Hurt
use multi-domain model instead of two-domainDRIT++ · Yosemite winter to summerLPIPS: 0.1183 -> 0.1204Improved
add multi-scale generator-discriminator instead of two more layers (ablation)DRIT++ high-resolution · GTA5 to CityscapeFID: 37.19 -> 28.62Improved

Later papers that compared with this method

20 later accepted papers report DRIT as a baseline in their results tables; 19 of them report a better number on most of the results they share with it.

12 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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