首站-论文投稿智能助手
典型文献
Co-occurrence based texture synthesis
文献摘要:
As image generation techniques mature,there is a growing interest in explainable representa-tions that are easy to understand and intuitive to manipulate.In this work,we turn to co-occurrence statistics,which have long been used for texture analysis,to learn a controllable texture synthesis model.We propose a fully convolutional generative adversarial network,conditioned locally on co-occurrence statistics,to generate arbitrarily large images while having local,interpretable control over texture appearance.To encourage fidelity to the input condition,we introduce a novel differentiable co-occurrence loss that is integrated seamlessly into our framework in an end-to-end fashion.We demonstrate that our solution offers a stable,intuitive,and interpretable latent representation for texture synthesis,which can be used to generate smooth texture morphs between different textures.We further show an interactive texture tool that allows a user to adjust local characteristics of the synthesized texture by directly using the co-occurrence values.
文献关键词:
作者姓名:
Anna Darzi;Itai Lang;Ashutosh Taklikar;Hadar Averbuch-Elor;Shai Avidan
作者机构:
Tel Aviv University,Tel Aviv 6997801,Israel;Cornell-Tech,Cornell University,NYC,NY,10044,USA
引用格式:
[1]Anna Darzi;Itai Lang;Ashutosh Taklikar;Hadar Averbuch-Elor;Shai Avidan-.Co-occurrence based texture synthesis)[J].计算可视媒体(英文),2022(02):289-302
A类:
B类:
Co,occurrence,synthesis,generation,techniques,mature,there,growing,interest,explainable,tions,that,are,easy,understand,intuitive,manipulate,In,this,turn,statistics,which,have,long,been,used,analysis,learn,controllable,model,We,propose,fully,convolutional,generative,adversarial,network,conditioned,locally,generate,arbitrarily,large,images,while,having,interpretable,over,appearance,To,encourage,fidelity,input,introduce,novel,differentiable,loss,integrated,seamlessly,into,framework,end,fashion,demonstrate,solution,offers,stable,latent,representation,can,smooth,morphs,between,textures,further,show,interactive,tool,allows,user,adjust,characteristics,synthesized,by,directly,using,values
AB值:
0.609857
相似文献
机标中图分类号,由域田数据科技根据网络公开资料自动分析生成,仅供学习研究参考。