论文标题
Xinggan for Person图像生成
XingGAN for Person Image Generation
论文作者
论文摘要
我们建议针对人形成的生成任务的新颖生成对抗网络（Xinggan或Crossinggan），即将给定人的姿势转化为所需的姿势。所提出的Xing Generator由两个生成分支组成，分别对人的外观和形状信息进行建模。此外，我们提出了两个新颖的块，以交叉方式有效地转移和更新人的形状和外观嵌入，以相互改进，这尚未被任何其他现有基于GAN的基于GAN的图像生成工作所考虑。在两个具有挑战性的数据集（即Market-1501和DeepFashion）上进行了广泛的实验，这表明拟议的Xinggan在客观的定量分数和主观的视觉真实性方面都可以提高最先进的表现。源代码和训练有素的模型可在https://github.com/ha0tang/xinggan上找到。
We propose a novel Generative Adversarial Network (XingGAN or CrossingGAN) for person image generation tasks, i.e., translating the pose of a given person to a desired one. The proposed Xing generator consists of two generation branches that model the person's appearance and shape information, respectively. Moreover, we propose two novel blocks to effectively transfer and update the person's shape and appearance embeddings in a crossing way to mutually improve each other, which has not been considered by any other existing GAN-based image generation work. Extensive experiments on two challenging datasets, i.e., Market-1501 and DeepFashion, demonstrate that the proposed XingGAN advances the state-of-the-art performance both in terms of objective quantitative scores and subjective visual realness. The source code and trained models are available at https://github.com/Ha0Tang/XingGAN.
