BriefGPT.xyz
Feb, 2020
对抗生成连续的隐式形状表示
Adversarial Generation of Continuous Implicit Shape Representations
HTML
PDF
Marian Kleineberg, Matthias Fey, Frank Weichert
TL;DR
本研究提出了一种基于有符号距离表示的生成对抗神经网络架构,能够生成高保真度的三维模型,并通过使用不同的 progressively growing voxel 网络作为鉴别器以及细化生成器能力的算法,从 ShapeNet 基准数据集中验证了其有效性。
Abstract
This work presents a
generative adversarial architecture
for generating three-dimensional shapes based on
signed distance representations
. While the deep generation of shapes has been mostly tackled by voxel and
→