图像上色 (Image-Colorization) 论文、代码大汇总

基于深度学习的图像上色论文、代码、demo的大汇总。图像上色方式包括全自动上色(Automatic Colorization)和用户交互上色(User Guided / Interaction Colorization)。

Github上持续更新https://github.com/MarkMoHR/Awesome-Image-Colorization

examples

目录

  • 全自动图像上色
  • 用户交互图像上色
    • 基于颜色提示的上色
    • 基于彩色参考图的上色
    • 基于颜色色块的上色
    • 基于语言/文字的上色

1. 全自动图像上色

论文发表处代码/项目链接
Learning Large-Scale Automatic Image ColorizationICCV 2015[project] [code]
Deep ColorizationICCV 2015
Learning Representations for Automatic ColorizationECCV 2016[project] [code]
Colorful Image ColorizationECCV 2016[project] [code]
Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous ClassificationSIGGRAPH 2016[project] [code]
Unsupervised Diverse Colorization via Generative Adversarial NetworksECML-PKDD 2017[code]
Learning Diverse Image ColorizationCVPR 2017[code]
Structural Consistency and Controllability for Diverse ColorizationECCV 2018
Pixelated Semantic Colorization1901.10889

2. 用户交互图像上色

2.1 基于颜色提示的上色

图像类型论文发表处代码/项目链接
漫画Manga colorizationSIGGRAPH 2006
线稿 / 草图Auto-painter: Cartoon Image Generation from Sketch by Using Conditional Generative Adversarial Networks1705.01908[code]
灰度自然图像Real-Time User-Guided Image Colorization with Learned Deep PriorsSIGGRAPH 2017[project] [code1] [code2]
草图Scribbler: Controlling Deep Image Synthesis with Sketch and ColorCVPR 2017
线稿User-Guided Deep Anime Line Art Colorization with Conditional Adversarial NetworksACM MM 2018[code]
线稿Two-stage Sketch ColorizationSIGGRAPH Asia 2018[code]
线稿 / 草图Outline Colorization through Tandem Adversarial NetworksOnline Demo[Demo] [code]
线稿Paints ChainerOnline Demo[Demo] [code]
线稿Style2paintsOnline Demo[Demo] [code]
漫画MangaCraftOnline Demo[Demo]

2.2 基于彩色参考图的上色

图像类型论文发表处代码/项目链接
漫画Comicolorization: Semi-Automatic Manga Colorization (also palette based)SIGGRAPH Asia 2017[code]
草图TextureGAN: Controlling Deep Image Synthesis with Texture PatchesCVPR 2018[code]
灰度自然图像Deep Exemplar-based ColorizationSIGGRAPH 2018[code]
灰度自然图像Example-Based Colourization Via Dense Encoding Pyramids (also palette based)Pacific Graphics 2018[code]
灰度自然图像A Superpixel-based Variational Model for Image ColorizationTVCG 2019

2.3 基于颜色色块的上色

图像类型论文发表处代码/项目链接
自然图像Palette-based Photo RecoloringSIGGRAPH 2015[project]
漫画Comicolorization: Semi-Automatic Manga Colorization (also reference based)SIGGRAPH Asia 2017[code]
灰度自然图像Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation (also text based)ECCV 2018[code]
灰度自然图像Example-Based Colourization Via Dense Encoding Pyramids (also reference based)Pacific Graphics 2018[code]

2.4 基于语言/文字的上色

图像类型论文发表处代码/项目链接
灰度自然图像 / 草图Language-Based Image Editing with Recurrent Attentive ModelsCVPR 2018[code]
灰度自然图像Coloring with Words: Guiding Image Colorization Through Text-based Palette Generation (also palette based)ECCV 2018[code]
场景草图LUCSS: Language-based User-customized Colorization of Scene Sketches1808.10544[code]
评论 10
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值