IEEE Trans Pattern Anal Mach Intell. 2022 Aug;44(8):4306-4320. doi: 10.1109/TPAMI.2021.3068236. Epub 2022 Jul 1.
This paper proposes a new generative adversarial network for pose transfer, i.e., transferring the pose of a given person to a target pose. We design a progressive generator which comprises a sequence of transfer blocks. Each block performs an intermediate transfer step by modeling the relationship between the condition and the target poses with attention mechanism. Two types of blocks are introduced, namely pose-attentional transfer block (PATB) and aligned pose-attentional transfer block (APATB). Compared with previous works, our model generates more photorealistic person images that retain better appearance consistency and shape consistency compared with input images. We verify the efficacy of the model on the Market-1501 and DeepFashion datasets, using quantitative and qualitative measures. Furthermore, we show that our method can be used for data augmentation for the person re-identification task, alleviating the issue of data insufficiency. Code and pretrained models are available at: https://github.com/tengteng95/Pose-Transfer.git.
本文提出了一种新的生成对抗网络用于姿态迁移，即将给定人物的姿态转换为目标姿态。我们设计了一个渐进式生成器，它由一系列传输块组成。每个块通过使用注意力机制来建模条件和目标姿态之间的关系来执行中间传输步骤。引入了两种类型的块，即姿态注意转移块（PATB）和对齐姿态注意转移块（APATB）。与之前的工作相比，我们的模型生成的人像图像更具真实感，与输入图像相比，保留了更好的外观一致性和形状一致性。我们使用定量和定性的测量方法在 Market-1501 和 DeepFashion 数据集上验证了模型的有效性。此外，我们还表明，我们的方法可用于人像重识别任务的数据增强，缓解数据不足的问题。代码和预训练模型可在：https://github.com/tengteng95/Pose-Transfer.git 获得。
