arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.00696cs.CVcs.AI
收藏

用于人物图像生成的深度图像空间变换

Deep Image Spatial Transformation for Person Image Generation

Peking University(北京大学);Peng Cheng Laboratory(鹏城实验室);Advanced Institute of Information Technology, Peking University(北京大学信息技术高等研究院)

Yurui Ren, Xiaoming Yu, Junming Chen, Thomas H. Li, Ge Li

摘要:

姿态引导的人物图像生成是将源人物图像变换为目标姿态。此任务需要对源数据进行空间操作。然而,卷积神经网络受到缺乏空间变换输入的能力的限制。在本文中,我们提出了一个可区分的全球流本地注意框架,重新组装的输入在功能级别。具体来说,我们的模型首先计算源和目标之间的全局相关性来预测流场。然后,从特征图中提取流动的局部补丁对以计算局部注意系数。最后,我们扭曲的源功能使用内容感知的采样方法与获得的局部注意力系数。主观和客观实验结果都证明了该模型的优越性。此外,在视频动画和视图合成的额外的结果表明,我们的模型是适用于其他需要空间变换的任务。我们的源代码可在https://github.com/RenYurui/Global-Flow-Local-Attention上获得。

英文摘要:

Pose-guided person image generation is to transform a source person image to a target pose. This task requires spatial manipulations of source data. However, Convolutional Neural Networks are limited by the lack of ability to spatially transform the inputs. In this paper, we propose a differentiable global-flow local-attention framework to reassemble the inputs at the feature level. Specifically, our model first calculates the global correlations between sources and targets to predict flow fields. Then, the flowed local patch pairs are extracted from the feature maps to calculate the local attention coefficients. Finally, we warp the source features using a content-aware sampling method with the obtained local attention coefficients. The results of both subjective and objective experiments demonstrate the superiority of our model. Besides, additional results in video animation and view synthesis show that our model is applicable to other tasks requiring spatial transformation. Our source code is available at https://github.com/RenYurui/Global-Flow-Local-Attention.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑