Variational Autoencoders for Deforming 3D Mesh Models
نویسندگان
چکیده
3D geometric contents are becoming increasingly popular. In this paper, we study the problem of analyzing deforming 3D meshes using deep neural networks. Deforming 3D meshes are flexible to represent 3D animation sequences as well as collections of objects of the same category, allowing diverse shapes with large-scale non-linear deformations. We propose a novel framework which we call mesh variational autoencoders (mesh VAE), to explore the probabilistic latent space of 3D surfaces. The framework is easy to train, and requires very few training examples. We also propose an extended model which allows flexibly adjusting the significance of different latent variables by altering the prior distribution. Extensive experiments demonstrate that our general framework is able to learn a reasonable representation for a collection of deformable shapes, and produce competitive results for a variety of applications, including shape generation, shape interpolation, shape space embedding and shape exploration, outperforming state-of-the-art methods.
منابع مشابه
3D Reconstruction of Non-Rigid Surfaces in Real-Time Using Wedge Elements
We present a new FEM (Finite Element Method) model for the 3D reconstruction of a deforming scene using as sole input a calibrated video sequence. Our approach extends the recently proposed 2D thin-plate FEM+EKF (Extended Kalman Filter) combination. Thinplate FEM is an approximation that models a deforming 3D thin solid as a surface, and then discretizes the surface as a mesh of planar triangle...
متن کاملInteractive Deformation of 3D Mesh Models
This paper proposes a framework for interactively deforming 3D mesh models. 3D mesh models are often used in finite element analysis, but existing surface-based deformation methods fail to deform volumetric elements consistently. In the method proposed here, vertices in a 3D mesh model are classified into boundary vertices and interior vertices. Boundary vertices are treated in the same way as ...
متن کاملHow to Train Deep Variational Autoencoders and Probabilistic Ladder Networks
Variational autoencoders are a powerful framework for unsupervised learning. However, previous work has been restricted to shallow models with one or two layers of fully factorized stochastic latent variables, limiting the flexibility of the latent representation. We propose three advances in training algorithms of variational autoencoders, for the first time allowing to train deep models of up...
متن کاملAdversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model. We introduce Adversarial Variational Bayes (AVB), a technique for training Variational Autoencoders with arbitrarily expressive inference mo...
متن کامل3D Models Recognition in Fourier Domain Using Compression of the Spherical Mesh up to the Models Surface
Representing 3D models in diverse fields have automatically paved the way of storing, indexing, classifying, and retrieving 3D objects. Classification and retrieval of 3D models demand that the 3D models represent in a way to capture the local and global shape specifications of the object. This requires establishing a 3D descriptor or signature that summarizes the pivotal shape properties of th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1709.04307 شماره
صفحات -
تاریخ انتشار 2017