3D Volumetric Modeling with Introspective Neural Networks
3D Volumetric Modeling with Introspective Neural Networks
复制标题
DOI：
10.1609/aaai.v33i01.33018481
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Wenlong Huang;B. Lai;Weijian Xu;Z. Tu
中科院分区：
文献类型：
--
作者：
Wenlong Huang;B. Lai;Weijian Xu;Z. Tu
在本文中，我们研究了三维体积建模问题，采用Wasserstein内省神经网络方法（WINN），以前适用于二维静态图像。我们将我们的算法命名为3DWINN，它在2D情况下具有与WINN相同的属性：同时生成和区分。与现有的3D体积建模方法相比，3DWINN在生成和分类任务的几个基准上都表现出了竞争力。除了标准的初始分数，Frechet初始距离（FID）指标也被用来衡量3D体积生成的质量。此外，我们还研究了针对体积数据的对抗性攻击，并展示了3DWINN对对抗性示例的鲁棒性，同时在单个模型中实现了分类和生成的吸引力结果。3DWINN是一个通用的框架，它可以应用于3D对象和场景建模的新兴任务。
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.1