Recently,there has been an upsurge of activity in image-based non-photorealistic rendering(NPR),and in particular portrait image stylisation,due to the advent of neural style transfer(NST).However,the state of performance evaluation in this field is poor,especially compared to the norms in the computer vision and machine learning communities.Unfortunately,the task of evaluating image stylisation is thus far not well defined,since it involves subjective,perceptual,and aesthetic aspects.To make progress towards a solution,this paper proposes a new structured,three-level,benchmark dataset for the evaluation of stylised portrait images.Rigorous criteria were used for its construction,and its consistency was validated by user studies.Moreover,a new methodology has been developed for evaluating portrait stylisation algorithms,which makes use of the different benchmark levels as well as annotations provided by user studies regarding the characteristics of the faces.We perform evaluation for a wide variety of image stylisation methods(both portrait-specific and general purpose,and also both traditional NPR approaches and NST)using the new benchmark dataset.

Paul L.Rosin;Yu-Kun Lai;David Mould;Ran Yi;Itamar Berger;Lars Doyle;Seungyong Lee;Chuan Li;Yong-Jin Liu;Amir Semmo;Ariel Shamir;Minjung Son;Holger Winnem?ller

School of Computer Science and Informatics,Cardiff University,Cardiff,UK;School of Computer Science,Carleton University,Ottawa,Canada;Department of Computer Science and Technology,Tsinghua University,Beijing,China;Reichman University(the Interdisciplinary Center),Herzliya,Israel;Department of Computer Science and Engineering,Pohang University of Science and Technology,Pohang,Republic of Korea;Lambda Labs,Inc.,San Francisco,USA;Hasso Plattner Institute,University of Potsdam,Potsdam,Germany;Multimedia Processing Laboratory,Samsung Advanced Institute of Technology,Suwon,Republic of Korea;Adobe Systems,Inc.,San Jose,USA

计算可视媒体（英文）

[1]Paul L.Rosin;Yu-Kun Lai;David Mould;Ran Yi;Itamar Berger;Lars Doyle;Seungyong Lee;Chuan Li;Yong-Jin Liu;Amir Semmo;Ariel Shamir;Minjung Son;Holger Winnem?ller-.NPRportrait 1.0:A three-level benchmark for non-photorealistic rendering of portraits)[J].计算可视媒体（英文）,2022(03):445-465

NPRportrait,stylisation,stylised

three,benchmark,photorealistic,rendering,portraits,Recently,there,has,been,upsurge,activity,particular,due,advent,neural,style,transfer,NST,However,state,performance,evaluation,this,field,poor,especially,compared,norms,computer,vision,machine,learning,communities,Unfortunately,task,evaluating,thus,far,well,defined,since,involves,subjective,perceptual,aesthetic,aspects,To,progress,towards,solution,paper,proposes,new,structured,dataset,images,Rigorous,criteria,were,used,construction,consistency,was,validated,by,user,studies,Moreover,methodology,developed,algorithms,which,makes,different,levels,annotations,provided,regarding,characteristics,faces,We,wide,variety,methods,both,specific,general,purpose,also,traditional,approaches,using

0.546781