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 Bloc ~(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.
翻译:本文提出一个新的变形对抗网络, 即将某人的姿势转换到目标姿势。 我们设计了一个渐进式生成器, 由传输区块的序列组成。 每个区块通过模拟条件与目标姿势之间的关系, 以关注机制为模型, 执行中间转移步骤。 引入了两类区块, 即Pose- 有意转移区块( PATB) 和 兼容的Pose- 有意转移区块 ~ (APATB) 。 与以往的工程相比, 我们的模型生成了更具真实性的人图像, 与输入图像相比, 保持了更好的外观一致性和形状的一致性。 我们使用定量和定性措施, 验证了市场( 1501) 模型和深时装数据集的功效。 此外, 我们显示, 我们的方法可用于个人再识别任务的数据增强, 减轻数据不足的问题。 代码和预设模型可在 https://github.com/tengeng95/Pose- Transfer.git上查阅。