摘要
近年来,随着三维模型资源的飞速增长,三维室内场景合成得到了广泛关注。目前计算机视觉领域中对场景布局知识学习和提取有较为丰富的研究,但忽视了场景合成中整体场景的色彩兼容性。因此,文中针对室内场景自动合成过程中的色彩设计展开研究,提出了一个基于数据驱动的室内场景着色模型。将室内场景着色过程中的颜色分配问题转化为优化问题,以参考场景的颜色主题作为约束条件建立了能量方程,求解得到场景内每个家具模型的颜色方案。结果表明,该方法能根据输入的参考场景图片自动合成布局合理且色彩和谐的虚拟室内场景。
In recent years,with the rapid growth of 3D model resources,3D indoor scene synthesis has received wide attention.At present,there are many studies on scene layout knowledge learning and extraction in the field of computer vision,but the color compatibility of the overall scene in scene synthesis has been overlooked.Therefore,this article conducts research on the color design in the automatic synthesis of indoor scenes and proposed a data-driven indoor scene coloring model.The color assignment problem in the indoor scene coloring process is transformed into an optimization problem,and the energy equation is established with the color theme of the reference scene as a constraint condtion to solve the color scheme of each furniture model in the scene.The results show that the method can automatically synthesize virtual indoor scenes with reasonable layout and harmonious colors based on the input reference scene images.
作者
赵国栋
何煜
ZHAO Guodong;HE Yu(School of Computer Science and Engineering,Tianjin University of Technology,Tianjin 300384,China;Key Laboratory of Space Utilization,Tehnology and Engineering Center for Space Utilization,Chinese Academy of Science,Beijing 100094,China)
出处
《天津理工大学学报》
2024年第2期100-105,共6页
Journal of Tianjin University of Technology
基金
天津理工大学教学改革重点项目(ZD20-13)。
关键词
场景合成
数据驱动
色彩兼容
室内设计
scene synthesis
data-driven
color compatibility
interior design
