Abstract
The estimation of 3D human body pose and shape from a single image has been extensively studied in recent years. However, the texture generation problem has not been fully discussed. In this paper, we propose an end-to-end learning strategy to generate textures of human bodies under the supervision of person re-identification. We render the synthetic images with textures extracted from the inputs and maximize the similarity between the rendered and input images by using the re-identification network as the perceptual metrics. Experiment results on pedestrian images show that our model can generate the texture from a single image and demonstrate that our textures are of higher quality than those generated by other available methods. Furthermore, we extend the application scope to other categories and explore the possible utilization of our generated textures.
Abstract (translated)
近年来,人们广泛地研究了从单个图像中估计人体三维姿态和形状的方法。然而,纹理生成问题还没有得到充分的讨论。本文提出了一种端到端的学习策略,在人的重新识别的监督下生成人体的纹理。我们使用从输入中提取的纹理来渲染合成图像,并使用重新识别网络作为感知度量,最大限度地提高渲染图像和输入图像之间的相似性。对行人图像的实验结果表明,我们的模型可以从单个图像中生成纹理,并且证明了我们的纹理比其他可用方法生成的纹理具有更高的质量。此外,我们将应用范围扩展到其他类别,并探索生成纹理的可能利用率。
URL
https://arxiv.org/abs/1904.03385