当前位置: X-MOL 学术Signal Image Video Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Video cloning for paintings via artistic style transfer
Signal, Image and Video Processing ( IF 2.3 ) Pub Date : 2020-07-07 , DOI: 10.1007/s11760-020-01730-3
Damon Shing-Min Liu , Ning Tu

In the past, visual arts usually represented the static art like paintings, photography and sculptures. In recent years, many museums, artwork galleries, and even art exhibitions demonstrated dynamic artworks for visitors to relish. The most famous dynamic artwork is “The moving painting of Along the River During the Qingming Festival”. Nevertheless, it took 2 years to complete this work. They had to plan each action for every character at first, then drew each video frame by animators. Finally, it could achieve seamless stitching by using lots of projectors to render scene on the screen. In our research, we develop a method for generating animated paintings. It only needs a number of videos on a network of existing databases and requires users to perform some simple auxiliary operations to achieve the effect of animation synthesis. First, our system lets users select an object with the same class from the first video frame. We then employ random forests as learning algorithm to retrieve from a video the object which users want to insert into an artwork. Second, we utilize style transferring, which enables the video frames to be consistent with the style of painting. At last, we use the seamless image cloning algorithm to yield seamless synthesizing result. Our approach allows different users to synthesize animating paintings up to their selected styled video frames. The resulting work not only maintains the original author’s painting style, but also generates a variety of artistic conception for people to enjoy.

中文翻译:

通过艺术风格转移的绘画视频克隆

过去,视觉艺术通常代表绘画、摄影和雕塑等静态艺术。近年来,许多博物馆、艺术画廊,甚至艺术展览都展示了充满活力的艺术品,供参观者津津乐道。最著名的动感作品是《清明上河图》。然而,完成这项工作花了两年时间。他们必须首先为每个角色计划每个动作,然后由动画师绘制每个视频帧。最后,它可以通过使用大量投影仪在屏幕上渲染场景来实现无缝拼接。在我们的研究中,我们开发了一种生成动画绘画的方法。它只需要现有数据库网络上的多个视频,并需要用户进行一些简单的辅助操作,即可达到动画合成的效果。第一的,我们的系统允许用户从第一个视频帧中选择具有相同类别的对象。然后,我们采用随机森林作为学习算法,从视频中检索用户想要插入到艺术品中的对象。其次,我们利用风格转移,使视频帧与绘画风格保持一致。最后,我们使用无缝图像克隆算法来产生无缝合成结果。我们的方法允许不同的用户将动画画合成到他们选择的风格视频帧。由此产生的作品既保持了原作者的绘画风格,又产生了多种意境供人们欣赏。然后,我们采用随机森林作为学习算法,从视频中检索用户想要插入到艺术品中的对象。其次,我们利用风格转移,使视频帧与绘画风格保持一致。最后,我们使用无缝图像克隆算法来产生无缝合成结果。我们的方法允许不同的用户将动画画合成到他们选择的风格视频帧。由此产生的作品既保持了原作者的绘画风格,又产生了多种意境供人们欣赏。然后,我们采用随机森林作为学习算法,从视频中检索用户想要插入到艺术品中的对象。其次,我们利用风格转移,使视频帧与绘画风格保持一致。最后,我们使用无缝图像克隆算法来产生无缝合成结果。我们的方法允许不同的用户将动画画合成到他们选择的风格视频帧。由此产生的作品既保持了原作者的绘画风格,又产生了多种意境供人们欣赏。我们的方法允许不同的用户将动画画合成到他们选择的风格视频帧。由此产生的作品既保持了原作者的绘画风格,又产生了多种意境供人们欣赏。我们的方法允许不同的用户将动画画合成到他们选择的风格视频帧。由此产生的作品既保持了原作者的绘画风格,又产生了多种意境供人们欣赏。
更新日期:2020-07-07
down
wechat
bug