Deformable Shape Completion with Graph Convolutional Autoencoders
نویسندگان
چکیده
The availability of affordable and portable depth sensors has made scanning objects and people simpler than ever. However, dealing with occlusions and missing parts is still a significant challenge. The problem of reconstructing a (possibly non-rigidly moving) 3D object from a single or multiple partial scans has received increasing attention in recent years. In this work, we propose a novel learning-based method for the completion of partial shapes. Unlike the majority of existing approaches, our method focuses on objects that can undergo non-rigid deformations. The core of our method is a variational autoencoder with graph convolutional operations that learns a latent space for complete realistic shapes. At inference, we optimize to find the representation in this latent space that best fits the generated shape to the known partial input. The completed shape exhibits a realistic appearance on the unknown part. We show promising results towards the completion of synthetic and real scans of human body and face meshes exhibiting different styles of articulation and partiality. GCONV (64) MEAN POOL GCONV (128) No BN .. .. LIN(16) GCONV (96) .. FC(2×128)
منابع مشابه
A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI
Segmentation of the left ventricle (LV) from cardiac magnetic resonance imaging (MRI) datasets is an essential step for calculation of clinical indices such as ventricular volume and ejection fraction. In this work, we employ deep learning algorithms combined with deformable models to develop and evaluate a fully automatic LV segmentation tool from short-axis cardiac MRI datasets. The method em...
متن کاملThe effect of whitening transformation on pooling operations in convolutional autoencoders
Convolutional autoencoders (CAEs) are unsupervised feature extractors for high-resolution images. In the preprocessing step, whitening transformation has widely been adopted to remove redundancy by making adjacent pixels less correlated. Pooling is a biologically inspired operation to reduce the resolution of feature maps and achieve spatial invariance in convolutional neural networks. Conventi...
متن کاملA Winner-Take-All Method for Training Sparse Convolutional Autoencoders
We explore combining the benefits of convolutional architectures and autoencoders for learning deep representations in an unsupervised manner. A major challenge is to achieve appropriate sparsity among hidden variables, since neighbouring variables in each feature map tend to be highly correlated and a suppression mechanism is therefore needed. Previously, deconvolutional networks and convoluti...
متن کاملVariational Autoencoders for Deforming 3D Mesh Models
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 vari...
متن کاملGenerative and Discriminative Voxel Modeling with Convolutional Neural Networks
When working with three-dimensional data, choice of representation is key. We explore voxel-based models, and present evidence for the viability of voxellated representations in applications including shape modeling and object classification. Our key contributions are methods for training voxel-based variational autoencoders, a user interface for exploring the latent space learned by the autoen...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1712.00268 شماره
صفحات -
تاریخ انتشار 2017