2 Hits in 3.1 sec

MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement [article]

Rinon Gal, Amit Bermano, Hao Zhang, Daniel Cohen-Or
2020 arXiv   pre-print
We present MRGAN, a multi-rooted adversarial network which generates part-disentangled 3D point-cloud shapes without part-based shape supervision.  ...  a set of loss terms designed with part disentanglement and shape semantics in mind.  ...  More recently, several works have shifted their attention to unsupervised Figure 1 : Network architecture of MRGAN, our multi-root 3D shape generator.  ... 
arXiv:2007.12944v1 fatcat:7twrpqwk5feftkughbzykwui4m

A Survey on Generative Adversarial Networks: Variants, Applications, and Training [article]

Abdul Jabbar, Xi Li, Bourahla Omar
2020 arXiv   pre-print
The Generative Models have gained considerable attention in the field of unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to its outstanding data  ...  generation capability.  ...  They used a 3D volumetric convolution network to generate 3D shapes in the generator, where they used 2D projected image as an input of discriminator to match synthesized 3D objects (fake object) with  ... 
arXiv:2006.05132v1 fatcat:gyjezuh5sfdilkp43ydsea5cwa