Pose Guided Human Image Synthesis with Partially Decoupled GAN
| Autor: | Wu, Jianhan, Wang, Jianzong, Si, Shijing, Qu, Xiaoyang, Xiao, Jing |
|---|---|
| Rok vydání: | 2022 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Pose Guided Human Image Synthesis (PGHIS) is a challenging task of transforming a human image from the reference pose to a target pose while preserving its style. Most existing methods encode the texture of the whole reference human image into a latent space, and then utilize a decoder to synthesize the image texture of the target pose. However, it is difficult to recover the detailed texture of the whole human image. To alleviate this problem, we propose a method by decoupling the human body into several parts (\eg, hair, face, hands, feet, \etc) and then using each of these parts to guide the synthesis of a realistic image of the person, which preserves the detailed information of the generated images. In addition, we design a multi-head attention-based module for PGHIS. Because most convolutional neural network-based methods have difficulty in modeling long-range dependency due to the convolutional operation, the long-range modeling capability of attention mechanism is more suitable than convolutional neural networks for pose transfer task, especially for sharp pose deformation. Extensive experiments on Market-1501 and DeepFashion datasets reveal that our method almost outperforms other existing state-of-the-art methods in terms of both qualitative and quantitative metrics. Comment: 16 pages, 14th Asian Conference on Machine Learning conference |
| Databáze: | arXiv |
| Externí odkaz: |
|