3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks

by   Mengwei Ren, et al.

Recently researchers have been shifting their focus towards learned 3D shape descriptors from hand-craft ones to better address challenging issues of the deformation and structural variation inherently present in 3D objects. 3D geometric data are often transformed to 3D Voxel grids with regular format in order to be better fed to a deep neural net architecture. However, the computational intractability of direct application of 3D convolutional nets to 3D volumetric data severely limits the efficiency (i.e. slow processing) and effectiveness (i.e. unsatisfied accuracy) in processing 3D geometric data. In this paper, powered with a novel design of adversarial networks (3D-A-Nets), we have developed a novel 3D deep dense shape descriptor (3D-DDSD) to address the challenging issues of efficient and effective 3D volumetric data processing. We developed new definition of 2D multilayer dense representation (MDR) of 3D volumetric data to extract concise but geometrically informative shape description and a novel design of adversarial networks that jointly train a set of convolution neural network (CNN), recurrent neural network (RNN) and an adversarial discriminator. More specifically, the generator network produces 3D shape features that encourages the clustering of samples from the same category with correct class label, whereas the discriminator network discourages the clustering by assigning them misleading adversarial class labels. By addressing the challenges posed by the computational inefficiency of direct application of CNN to 3D volumetric data, 3D-A-Nets can learn high-quality 3D-DSDD which demonstrates superior performance on 3D shape classification and retrieval over other state-of-the-art techniques by a great margin.


page 3

page 4


VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes

Voxel is an important format to represent geometric data, which has been...

Wide and deep volumetric residual networks for volumetric image classification

3D shape models that directly classify objects from 3D information have ...

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

We study the problem of 3D object generation. We propose a novel framewo...

VConv-DAE: Deep Volumetric Shape Learning Without Object Labels

With the advent of affordable depth sensors, 3D capture becomes more and...

A Convolutional Autoencoder Approach to Learn Volumetric Shape Representations for Brain Structures

We propose a novel machine learning strategy for studying neuroanatomica...

Learning Descriptor Networks for 3D Shape Synthesis and Analysis

This paper proposes a 3D shape descriptor network, which is a deep convo...

Decorrelating Adversarial Nets for Clustering Mobile Network Data

Deep learning will play a crucial role in enabling cognitive automation ...

Please sign up or login with your details

Forgot password? Click here to reset