Filters








2 Hits in 3.8 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.  ...  Model Conclusions We presented MRGAN, a multi-rooted architecture that addresses the challenging task of learning a part-disentangled representation in an unsupervised manner.  ... 
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  ...  Many models of GAN have proposed, and several practical applications emerged in various domains of computer vision and machine learning.  ...  Recently, the Disentangled Representation Net (DRNET) [170] approach learns disentangled image representations from the video.  ... 
arXiv:2006.05132v1 fatcat:gyjezuh5sfdilkp43ydsea5cwa