arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01587cs.CV
收藏

3D人体造型风格转换

3D Human Shape Style Transfer

Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Grenoble INP(格勒诺布尔国立综合理工学院)

Joao Regateiro, Edmond Boyer

摘要:

我们考虑的问题修改/替换的形状风格的一个真正的移动字符与一个任意的静态真正的源字符。传统的解决方案遵循的姿势转移策略,从移动的字符到源字符形状,这依赖于骨骼姿势参数化。在本文中,我们探索了一种替代方法,将源形状风格转移到移动字符上。预期的好处是,以避免固有的困难的姿势形状转换所需的骨架参数化应用于真实的字符。为了这个目的,我们考虑图像风格转移技术,并研究如何使它们适应3D人体形状。自适应实例规范化(AdaIN)和SPADE架构已被证明可以有效和准确地将一个图像的风格转移到另一个图像上,同时保留原始图像结构。其中AdaIN贡献了一个模块,通过主题的统计来执行风格转换,SPADE贡献了一个残差块架构来改进风格转换的质量。我们证明,这些方法是可扩展到3D形状域,提出了一个卷积神经网络,适用于相同的原则,保持形状结构(形状姿势),同时转移的风格,一个新的主题形状。生成的结果通过一个模拟模块进行监督,以评估形状的真实性,同时强制解码器合成合理的形状,并改善未见过的主题的风格转移。我们的实验表明,平均$\approx 56\%$定性和定量的改进,通过基于优化和基于学习的方法在形状转移的基线。

英文摘要:

We consider the problem of modifying/replacing the shape style of a real moving character with those of an arbitrary static real source character. Traditional solutions follow a pose transfer strategy, from the moving character to the source character shape, that relies on skeletal pose parametrization. In this paper, we explore an alternative approach that transfers the source shape style onto the moving character. The expected benefit is to avoid the inherently difficult pose to shape conversion required with skeletal parametrization applied on real characters. To this purpose, we consider image style transfer techniques and investigate how to adapt them to 3D human shapes. Adaptive Instance Normalisation (AdaIN) and SPADE architectures have been demonstrated to efficiently and accurately transfer the style of an image onto another while preserving the original image structure. Where AdaIN contributes with a module to perform style transfer through the statistics of the subjects and SPADE contribute with a residual block architecture to refine the quality of the style transfer. We demonstrate that these approaches are extendable to the 3D shape domain by proposing a convolutional neural network that applies the same principle of preserving the shape structure (shape pose) while transferring the style of a new subject shape. The generated results are supervised through a discriminator module to evaluate the realism of the shape, whilst enforcing the decoder to synthesise plausible shapes and improve the style transfer for unseen subjects. Our experiments demonstrate an average of $\approx 56\%$ qualitative and quantitative improvements over the baseline in shape transfer through optimization-based and learning-based methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑