[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120274-en":3,"doc-seo-120274-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},120274,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine Learning for Generative Painting Informed by Visual Arts - Investigating Painting Techniques for Designing Machine Learning Pipelines","Visual art practice is a multifaceted creative process shaped by an artist’s style and preferences. While many studies apply artificial intelligence to art production and statistical analysis, there remains substantial room to integrate these techniques into generative painting pipelines grounded in machine learning. This master’s thesis uses a research-through-design approach to analyze painting techniques and formulates tasks such as artwork segmentation, stroke prediction, and pipeline-based presentations of painting processes. Results indicate that photo-trained segmentation models are difficult to apply directly to artwork components, motivating improvement directions.","Machine Learning for generative painting informed by visual arts  \nInvestigating painting techniques for designing Machine Learning pipelines of generative painting  \nMaster’s thesis in Computer science and engineering  \nCHAOMING WANG  \nDepartment of Computer Science and Engineering CHALMERS UNIVERSITY OF TECHNOLOGY UNIVERSITY OF GOTHENBURG  \nGothenburg, Sweden 2023  \nMaster’s thesis 2023  \nMachine Learning for generative painting informed by visual arts  \nInvestigating painting techniques for designing Machine Learning pipelines of generative painting  \nCHAOMING WANG  \nDepartment of Computer Science and Engineering Chalmers University of Technology University of Gothenburg Gothenburg, Sweden 2023  \nCHAOMING WANG  \n© CHAOMING WANG, 2023 .  \nSupervisor: Kıvanç Tatar, Department of Computer Science and Engineering Examiner: Palle Dahlstedt, Department of Computer Science and Engineering  \nMaster’s Thesis 2023  \nDepartment of Computer Science and Engineering  \nChalmers University of Technology and University of Gothenburg SE-412 96 Gothenburg  \nTelephone +46 76 397 6889  \nTypeset in LATEX  \nGothenburg, Sweden 2023  \nMachine Learning for generative painting informed by visual arts  \nInvestigating painting techniques for designing Machine Learning pipelines of generative painting  \nCHAOMING WANG  \nDepartment of Computer Science and Engineering  \nChalmers University of Technology and University of Gothenburg  \nAbstract  \nVisual art practice is a complicated, varied, creative process based on the artist’s style and preferences. Although many studies have attempted to apply artificial intelligence techniques to art production and statistical analysis, there is still significant scope for exploring how to incorporate the techniques in visual arts practices into generative painting pipelines using Machine Learning. This thesis applies machine learning to analyzing painting techniques in painting practices with a research-through-design approach. The problem is mainly presented as tasks such as segmentation of artworks (in this thesis, paintings), stroke prediction, and the presentation of painting processes based on different painting techniques through different algorithmic pipelines. The results show that most segmentation models based on photo training are challenging to apply to the segmentation of artwork components directly, and relevant improvement solutions are discussed in Chapter 6. In addition, due to the diverse presentation of painting art, this paper presents different painting techniques based on the foreground and background segmentation and ’blocking-in’ techniques based on line detection. It discusses the possibility of transferring these painting processes to other painting processes.  \nKeywords: painting techniques, visual art, image segmentation, machine learning.  \nAcknowledgements  \nCompleting this thesis would not have been possible without the help of many people. I extend my sincere gratitude to everyone who has contributed to my thesis, in ways both big and small. I am truly fortunate to have such a supportive network of people around me, and I am grateful for the opportunity to have undertaken this research.  \nI would like to express my sincere gratitude to my supervisor Kıvanç Tatar, for his patience, guidance, and support. I have gained a lot during the project, both in the task-related topics and the ability of art perception and appreciation. Most importantly, I received professional and constructive guidance on doing research. Iam truly grateful for their mentorship and for pushing me to achieve my best work.  \nI would also like to express my gratitude to the esteemed professors in Chalmers, whose teachings and guidance have shaped my research and contributed significantly to my intellectual growth. In particular, I would like to express my gratitude to Lennart Svensson, the professor of the deep learning course, for his extensive coverage of the field of deep learning and generative art, and I have foun","cbCaih4KZrW4uXgq","https://ap.wps.com/l/cbCaih4KZrW4uXgq","pdf",57839170,1,81,"English","en",105,"# Abstract\n# Keywords\n# Acknowledgements\n# List of Acronyms\n## DALLE\n## CNN\n## GAN\n## VQ-VAE\n## LDMs","[{\"question\":\"What approach does the thesis use to apply machine learning to painting?\",\"answer\":\"It applies machine learning using a research-through-design approach to analyze painting techniques in practice.\"},{\"question\":\"Which core tasks are used to model generative painting pipelines?\",\"answer\":\"The work presents segmentation of paintings, stroke prediction, and algorithmic pipelines that present painting processes using different techniques.\"},{\"question\":\"What key finding is reported about artwork segmentation models?\",\"answer\":\"Segmentation models trained on photos are challenging to apply directly to segment components of artworks, and solutions for improvement are discussed later in the thesis.\"}]","Machine Learning for Generative Painting Informed by Visual Arts - Investigating Painting Techniques for Designing Machine Learning Pipelines | PDF",1785729192,204,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-for-generative-painting-informed-by-visual-arts-investigating-painting-techniques-for-designing-machine-learning-pipelines","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-for-generative-painting-informed-by-visual-arts-investigating-painting-techniques-for-designing-machine-learning-pipelines/120274/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What approach does the thesis use to apply machine learning to painting?","Question",{"text":75,"@type":76},"It applies machine learning using a research-through-design approach to analyze painting techniques in practice.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which core tasks are used to model generative painting pipelines?",{"text":80,"@type":76},"The work presents segmentation of paintings, stroke prediction, and algorithmic pipelines that present painting processes using different techniques.",{"name":82,"@type":73,"acceptedAnswer":83},"What key finding is reported about artwork segmentation models?",{"text":84,"@type":76},"Segmentation models trained on photos are challenging to apply directly to segment components of artworks, and solutions for improvement are discussed later in the thesis.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]