论文阅读【CVPR-2022】3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swappi

3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces

通过小批量特征互换实现身体和脸部的三维形状变异自动编码器潜移默化

studyai.com

搜索论文: 3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces

摘要(Abstract)

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem.The problem is particularly acute when control over identity features is required.

在人脸和身体的三维生成模型中，学习一种分离的、可解释的、结构化的潜在表达仍然是一个有待解决的问题。当需要在身份特征(同一本体特征)上进行控制时，这个问题尤其严重。

In this paper, we propose an intuitive yet effective self-supervised approach to train a 3D shape variational autoencoder (VAE) which encourages a disentangled latent representation of identity features.

在本文中，我们提出了一种直观而有效的自监督方法来训练一个3D形状变分自动编码器（VAE），它能够支持和促进本体特征的分离潜在表示(表达)。
代码和预训练模型： github.com/simofoti/3DVAE-SwapDisentangled.

Curating the mini-batch generation by swapping arbitrary features across different shapes allows to define a loss function leveraging known differences and similarities in the latent representations.

通过在不同形状之间交换任意数量的特征来辅助小批量生成，可以利用潜在表示中的已知差异和相似性来定义损失函数。

Experimental results conducted on 3D meshes show that state-of-the-art methods for latent disentanglement are not able to disentangle identity features of faces and bodies.

在三维网格上进行的实验结果表明，现有的潜在解纠缠方法无法解纠缠人脸和身体的身份本体特征。

Our proposed method properly decouples the generation of such features while maintaining good representation and reconstruction capabilities.
我们提出的方法在保持良好的表示能力和重建能力的同时，适当地解耦了这些特征的生成。