The generation of well-designed artwork is often quite time-consuming and assumes a high degree of proficiency on part of the human painter. In order to facilitate the human painting process, substantial research efforts have been made on teaching machines how to "paint like a human", and then using the trained agent as a painting assistant tool for human users. However, current research in this direction is often reliant on a progressive grid-based division strategy wherein the agent divides the overall image into successively finer grids, and then proceeds to paint each of them in parallel. This inevitably leads to artificial painting sequences which are not easily intelligible to human users. To address this, we propose a novel painting approach which learns to generate output canvases while exhibiting a more human-like painting style. The proposed painting pipeline Intelli-Paint consists of 1) a progressive layering strategy which allows the agent to first paint a natural background scene representation before adding in each of the foreground objects in a progressive fashion. 2) We also introduce a novel sequential brushstroke guidance strategy which helps the painting agent to shift its attention between different image regions in a semantic-aware manner. 3) Finally, we propose a brushstroke regularization strategy which allows for ~60-80% reduction in the total number of required brushstrokes without any perceivable differences in the quality of the generated canvases. Through both quantitative and qualitative results, we show that the resulting agents not only show enhanced efficiency in output canvas generation but also exhibit a more natural-looking painting style which would better assist human users express their ideas through digital artwork.
Historic Emergence of Diversity in Painting: Heterogeneity in Chromatic Distance in Images and Characterization of Massive Painting Data Set
Korea Advanced Institute of Science and Technology（韩国高等科学技术院）；Samsung SDS（三星SDS）；The Asia Institute（亚洲研究所）；Ministry of Foreign Affairs（外交部）；Asia Pacific Center for Theoretical Physics（亚太理论物理中心）；University of Cambridge（剑桥大学）
Identifying centres of interest in paintings using alignment and edge detection: Case studies on works by Luc Tuymans
Ege University（埃格大学）；Catalan Institut for Advanced Studies (ICREA)（加泰罗尼亚高级研究所（ICREA））；Institute for Evolutionary Biology (UPF-CSIC)（进化生物学研究所（UPF-CSIC））
Emergence of Painting Ability via Recognition-Driven Evolution
Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；RIKEN（理化学研究所）；The University of Tokyo（东京大学）；Tianjin Academy of Fine Art（天津美术学院）；Sakana AI
Inversion-Based Style Transfer with Diffusion Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of AI, UCAS（中国科学院大学人工智能学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Kuaishou Technology（快手科技）
