* Accepted to NeurIPS2021. We propose Generative Occupancy Fields(GOF),
a 3D-aware generative model which could synthesize realistic images with 3D
consistency and simultaneously learn compact object surfaces Access Paper or Ask Questions
* Accepted to NeurIPS2021. We proposed ShadeGAN, which could perform
shape-accurate 3D-aware image synthesis by modeling shading in generative
implicit models Access Paper or Ask Questions