We study the problem of 3D object generation. We propose a novel framework,
namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects
from a probabilistic space by leveraging recent advances in volumetric
convolutional networks and generative adversarial nets. The benefits of our
model are three-fold: first, the use of an adversarial criterion, instead of
traditional heuristic criteria, enables the generator to capture object
structure implicitly and to synthesize high-quality 3D objects; second, the
generator establishes a mapping from a low-dimensional probabilistic space to
the space of 3D objects, so that we can sample objects without a reference
image or CAD models, and explore the 3D object manifold; third, the adversarial
discriminator provides a powerful 3D shape descriptor which, learned without
supervision, has wide applications in 3D object recognition. Experiments
demonstrate that our method generates high-quality 3D objects, and our
unsupervisedly learned features achieve impressive performance on 3D object
recognition, comparable with those of supervised learning methods.

本文提出了一种新颖的框架，即 3D 生成对抗网络（3D-GAN），通过利用体积卷积网络和生成对抗网络的最新进展，从概率空间生成 3D 对象，并具有生成高质量 3D 对象、无先验 CAD 模型或图像依赖性、生成器从低维概率空间到 3D 空间的映射以及训练出的无监督深度学习的 3D 描述符等优点，在 3D 对象生成及识别等方面取得了令人印象深刻的性能。