Multi-Attribute Guided Painting Generation | |
Lin, Minxuan2,4; Deng, Yingying2,4; Fan, Tang3; Dong, Weiming1,2; Xu, Changsheng2 | |
2020 | |
会议日期 | AUG 06-08, 2020 |
会议地点 | ELECTR NETWORK |
页码 | 400-403 |
英文摘要 | Controllable painting generation plays a pivotal role in image stylization. Currently, the control way of style transfer is subject to exemplar-based reference or a random one-hot vector guidance. Few works focus on decoupling the intrinsic properties of painting as control conditions, e.g., artist, genre and period. Under this circumstance, we propose a novel framework adopting multiple attributes from the painting to control the stylized results. An asymmetrical cycle structure is equipped to preserve the fidelity, associating with style preserving and attribute regression loss to keep the unique distinction of colors and textures between domains. Several qualitative and quantitative results demonstrate the effect of the combinations of multiple attributes and achieve satisfactory performance. |
会议录出版者 | IEEE |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/45051] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
通讯作者 | Dong, Weiming |
作者单位 | 1.CASIA-LLVision Joint Lab 2.NLPR, CASIA 3.Fosafer 4.School of AI, UCAS |
推荐引用方式 GB/T 7714 | Lin, Minxuan,Deng, Yingying,Fan, Tang,et al. Multi-Attribute Guided Painting Generation[C]. 见:. ELECTR NETWORK. AUG 06-08, 2020. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论