论文标题
必须gan：自动驱动人员形象的多层次统计转移
MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation
论文作者
论文摘要
姿势指导的人图像产生通常涉及使用配对的源目标图像来监督培训，这大大增加了数据准备工作并限制了模型的应用。为了解决这个问题，我们提出了一种新型的多级统计转移模型，该模型将其从人图像中解散和传输多层外观特征，并将其与姿势功能合并，以重建源人员图像本身。因此，可以将源图像用作自我驱动人员形象产生的监督。具体而言，我们的模型从外观编码器中提取多层次特征，并通过注意机制和属性统计来学习最佳的外观表示。然后，我们将它们转移到姿势引导的发生器中，以重新融合外观和姿势。我们的方法可以灵活地操纵人外观和姿势特性，以执行姿势转移和服装风格转移任务。 DeepFashion数据集的实验结果证明了我们方法的优势与最先进的监督和无监督的方法相比。此外，我们的方法在野外还表现良好。
Pose-guided person image generation usually involves using paired source-target images to supervise the training, which significantly increases the data preparation effort and limits the application of the models. To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves. So that the source images can be used as supervision for self-driven person image generation. Specifically, our model extracts multi-level features from the appearance encoder and learns the optimal appearance representation through attention mechanism and attributes statistics. Then we transfer them to a pose-guided generator for re-fusion of appearance and pose. Our approach allows for flexible manipulation of person appearance and pose properties to perform pose transfer and clothes style transfer tasks. Experimental results on the DeepFashion dataset demonstrate our method's superiority compared with state-of-the-art supervised and unsupervised methods. In addition, our approach also performs well in the wild.
