AI Paper Atlas

Research map / Image generation / Image restoration

ColorFormer: Image Colorization via Color Memory Assisted Hybrid-Attention Transformer

Xiaozhong Ji, Boyuan Jiang, Donghao Luo, Guangpin Tao, Wenqing Chu, Zhifeng Xie, Chengjie Wang, Ying Tai

ECCV 2022 · Image generation › Image restoration · approach: Image harmonization and color transformation · 67 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
replace ResNet50 encoder with Swin-Transformer (ablation)ColorFormer w/o CM · ImageNet valFID: 4.10 -> 2.68Improved
replace Swin-Transformer with GLH-Transformer encoder (ablation)ColorFormer w/o CM · ImageNet valFID: 2.68 -> 1.85Improved
replace Twins with GLH-Transformer encoder (ablation)ColorFormer w/o CM · ImageNet valFID: 2.48 -> 1.85Improved
add Color Memory module (one group) (ablation)ColorFormer GLH-Transformer · ImageNet valFID: 1.85 -> 1.71Improved
add Color Memory module (four groups) (ablation)ColorFormer GLH-Transformer · ImageNet valCF: 36.70 -> 39.76Improved
use four groups of color priors instead of one (ablation)ColorFormer · ImageNet valCF: 36.96 -> 39.76Improved
initialize memory with Memory Build clustering instead of random (ablation)ColorFormer CM4 · ImageNet valFID: 1.80 -> 1.71Improved
increase memory size m from 256 to 1024 (ablation)ColorFormer CM · ImageNet valFID: 1.93 -> 1.68Improved
increase color embedding dimension d2 from 128 to 512 (ablation)ColorFormer CM · ImageNet valFID: 1.91 -> 1.65Improved
reduce semantic dimension k from 128 to 32 (ablation)ColorFormer CM · ImageNet valFID: 1.78 -> 1.87Hurt
use ColorFormer instead of Wu et al. (GAN-prior colorization)automatic colorization · ImageNet valFID: 3.62 -> 1.71Improved

Later papers that compared with this method

2 later accepted papers report ColorFormer as a baseline in their results tables; 1 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