Controllable person image generation aims to produce realistic human images with desirable attributes such as a given pose, cloth textures, or hairstyles. However, the large spatial misalignment between source and target images makes the standard image-to-image translation architectures unsuitable for this task. Most state-of-the-art methods focus on alignment for global pose-transfer tasks. However, they fail to deal with region-specific texture-transfer tasks, especially for person images with complex textures. To solve this problem, we propose a novel Spatially-Adaptive Warped Normalization (SAWN) which integrates a learned flow-field to warp modulation parameters. It allows us to efficiently align person spatially-adaptive styles with pose features. Moreover, we propose a novel Self-Training Part Replacement (STPR) strategy to refine the model for the texture-transfer task, which improves the quality of the generated clothes and the preservation ability of non-target regions. Our experimental results on the widely used DeepFashion dataset demonstrate a significant improvement of the proposed method over the state-of-the-art methods on pose-transfer and texture-transfer tasks. The code is available at https://github.com/zhangqianhui/Sawn.
翻译:可控制的人图像生成旨在产生符合人类现实的图像,其属性如给定的姿势、布质或发型等。然而,源和目标图像之间的巨大空间偏差使得标准图像到图像翻译结构不适合这项任务。大多数最先进的方法侧重于全球造型转移任务的一致性。然而,它们未能处理特定区域的质质地转移任务,特别是具有复杂质地的人图像。为了解决这个问题,我们提议了一个新的空间-Adaptial Warped 正常化(SAWN),将一个学习的流地与扭曲调制参数相结合。它使我们能够有效地将个人空间-感化风格与外貌特征相协调。此外,我们提议了一个全新的自我培训部分替换战略,以完善制式转移任务的模式,从而改进生成的服装的质量和非目标区域的保存能力。我们在广泛使用的深时尚数据集(SAWN)的实验结果,展示了在状态-ax-ab-modal-modaltractions 上拟议的方法的重大改进。关于制式/制式/制式/制式/制式系统格式转让的系统方法。