Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
This addresses the problem of generating and recognizing 3D objects without supervision, offering a novel approach for computer vision and graphics applications.
The paper tackled 3D object generation by proposing 3D-GAN, a framework that generates high-quality 3D objects from a probabilistic latent space and learns unsupervised features for recognition, achieving performance comparable to supervised methods.
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.