AI Paper Atlas

Research map / Image generation / Editing and style transfer

BigColor: Colorization Using a Generative Color Prior for Natural Images

Geonung Kim, Kyoungkook Kang, Seongtae Kim, Hwayoon Lee, Sehoon Kim, Jonghyun Kim, Seung-Hwan Baek, Sunghyun Cho

ECCV 2022 · Image generation › Editing and style transfer · approach: Texture and sketch synthesis · 81 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 color augmentation to discriminator real images (ablation)BigColor · ImageNet-1K valcolorfulness: 36.157 -> 40.006Improved
add color augmentation to discriminator real images (ablation)BigColor · ImageNet-1K valFID: 1.288 -> 1.243Improved
also augment the generated image (ablation)BigColor · ImageNet-1K valFID: 1.243 -> 1.604Hurt
initialize G and D from pretrained BigGAN (ablation)BigColor · ImageNet 100-class subsetFID: 7.201 -> 5.714Improved
initialize only G from pretrained BigGAN (ablation)BigColor · ImageNet 100-class subsetFID: 7.201 -> 8.058Mixed
add adversarial loss (ablation)BigColor · ImageNet 100-class subsetFID: 7.692 -> 5.714Improved
add adversarial loss (ablation)BigColor · ImageNet 100-class subsetclassification accuracy: 75.52 -> 81.44Improved
add residual learning to encoder (ablation)BigColor · ImageNet 100-class subsetFID: 6.523 -> 5.980Improved
add class-conditioned batch normalization to encoder (ablation)BigColor · ImageNet 100-class subsetFID: 5.980 -> 5.714Improved
add plain batch normalization without residual learning (ablation)BigColor encoder · ImageNet 100-class subsetFID: 6.523 -> 7.286Hurt
increase spatial feature resolution to 64x64 (ablation)BigColor · ImageNetFIDMixed
use BigColor instead of ToVivid on complex imagesBigColor · ImageNet-1K val (100 complex images)classification accuracy: 65.000 -> 74.000Improved

Later papers that compared with this method

2 later accepted papers report BigColor 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