AI Paper Atlas

Research map / Image generation / Editing and style transfer

IICNet: A Generic Framework for Reversible Image Conversion

Ka Leong Cheng, Yueqi Xie, Qifeng Chen

ICCV 2021 · Image generation › Editing and style transfer · approach: Image-to-image translation · 31 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 the relation module (ablation)IICNet · video embeddingembedding PSNR: 38.752 -> 38.900Improved
add the relation module (ablation)IICNet · video embeddingrestored PSNR: 41.159 -> 41.729Improved
add the relation module (ablation)IICNet · mononizing binocular imagesrestored PSNR: 39.667 -> 41.649Improved
add the relation module (ablation)IICNet · hiding images in an imagerestored PSNR: 36.698 -> 37.935Improved
add the frequency loss (ablation)IICNet · video embeddingembedding PSNR: 32.914 -> 38.900Improved
add the frequency loss (ablation)IICNet · video embeddingrestored PSNR: 42.353 -> 41.729Hurt
add the frequency loss (ablation)IICNet · hiding images in an imageembedding PSNR: 28.780 -> 35.641Improved
add the frequency loss (ablation)IICNet · mononizing binocular imagesembedding PSNR: 31.469 -> 37.540Improved
use IICNet instead of an auto-encoder (AE) baseline (ablation)IICNet · hiding images in an imagerestored PSNR: 31.721 -> 37.935Improved
use IICNet instead of the INN-with-auxiliary-maps baseline (ablation)IICNet · video embeddingembedding PSNR: 34.029 -> 38.900Improved
use IICNet instead of Zhu et al. at time step 5IICNet · DAVIS 2017 video embeddingembedding PSNR: 24.246 -> 36.739Improved
increase embedding range from 5 to 9 imagesIICNet · DAVIS 2017 video embeddingrestored PSNR: 41.729 -> 36.698Hurt

Later papers that compared with this method

2 later accepted papers report IICNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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