A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
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
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