3D Volumetric Modeling with Introspective Neural Networks
Authors:
Open Access
- 17 July 2019
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 33 (01) , 8481-8488
Abstract
In this paper, we study the 3D volumetric modeling problem by adopting the Wasserstein introspective neural networks method (WINN) that was previously applied to 2D static images. We name our algorithm 3DWINN which enjoys the same properties as WINN in the 2D case: being simultaneously generative and discriminative. Compared to the existing 3D volumetric modeling approaches, 3DWINN demonstrates competitive results on several benchmarks in both the generation and the classification tasks. In addition to the standard inception score, the Frechet Inception Distance (FID) metric is´ also adopted to measure the quality of 3D volumetric generations. In addition, we study adversarial attacks for volumetric data and demonstrate the robustness of 3DWINN against adversarial examples while achieving appealing results in both classification and generation within a single model. 3DWINN is a general framework and it can be applied to the emerging tasks for 3D object and scene modeling.1Keywords
This publication has 16 references indexed in Scilit:
- Learning Descriptor Networks for 3D Shape Synthesis and Analysis2018
- Attentional ShapeContextNet for Point Cloud Recognition2018
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image2017
- VConv-DAE: Deep Volumetric Shape Learning Without Object Labels2016
- Volumetric and Multi-view CNNs for Object Classification on 3D Data2016
- Deep Residual Learning for Image Recognition2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- 3D ShapeNets: A deep representation for volumetric shapes2015
- Going deeper with convolutions2015
- Learning Generative Models via Discriminative Approaches2007