计算机科学
人工智能
计算机视觉
动画
特征(语言学)
杠杆(统计)
光流
像素
薄板样条
图像(数学)
计算机图形学(图像)
哲学
语言学
双线性插值
样条插值
出处
期刊:Cornell University - arXiv
日期:2022-01-01
被引量:1
标识
DOI:10.48550/arxiv.2203.14367
摘要
Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images. In this paper, a new end-to-end unsupervised motion transfer framework is proposed to overcome such issue. Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image. Secondly, in order to restore the missing regions more realistically, we leverage multi-resolution occlusion masks to achieve more effective feature fusion. Finally, additional auxiliary loss functions are designed to ensure that there is a clear division of labor in the network modules, encouraging the network to generate high-quality images. Our method can animate a variety of objects, including talking faces, human bodies, and pixel animations. Experiments demonstrate that our method performs better on most benchmarks than the state of the art with visible improvements in pose-related metrics.
科研通智能强力驱动
Strongly Powered by AbleSci AI