...
首页> 外文期刊>ACM Transactions on Graphics >Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification
【24h】

Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification

机译:让有颜色!:全局和局部图像先验的端到端联合学习,以实现同时分类的自动图像着色

获取原文
获取原文并翻译 | 示例
           

摘要

We present a novel technique to automatically colorize grayscalernimages that combines both global priors and local image features.rnBased on Convolutional Neural Networks, our deep network featuresrna fusion layer that allows us to elegantly merge local informationrndependent on small image patches with global priors computedrnusing the entire image. The entire framework, including thernglobal and local priors as well as the colorization model, is trainedrnin an end-to-end fashion. Furthermore, our architecture can processrnimages of any resolution, unlike most existing approaches based onrnCNN. We leverage an existing large-scale scene classification databasernto train our model, exploiting the class labels of the dataset tornmore efficiently and discriminatively learn the global priors. Wernvalidate our approach with a user study and compare against thernstate of the art, where we show significant improvements. Furthermore,rnwe demonstrate our method extensively on many differentrntypes of images, including black-and-white photography from overrna hundred years ago, and show realistic colorizations.
机译:我们提出了一种新颖的自动对灰度图像进行着色的技术,该技术结合了全局先验和局部图像特征。rn基于卷积神经网络,我们的深层网络特征融合层使我们能够优雅地合并依赖于小图像斑块的局部信息与通过使用整个图像计算的全局先验。整个框架(包括全局和局部先验以及着色模型)以端到端的方式进行培训。此外,与大多数现有的基于CNN的方法不同,我们的体系结构可以处理任何分辨率的图像。我们利用现有的大型场景分类数据库来训练我们的模型,利用数据集的类标签更有效地撕裂并有区别地学习全局先验。通过用户研究对我们的方法进行验证,并与最新技术进行比较,我们在此方面取得了显着进步。此外,我们在许多不同类型的图像上(包括一百多年前的黑白摄影)广泛展示了我们的方法,并显示了逼真的色彩。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号