Generative Models for 3D Point Clouds

02/26/2023
by   Lingjie Kong, et al.
0

Point clouds are rich geometric data structures, where their three dimensional structure offers an excellent domain for understanding the representation learning and generative modeling in 3D space. In this work, we aim to improve the performance of point cloud latent-space generative models by experimenting with transformer encoders, latent-space flow models, and autoregressive decoders. We analyze and compare both generation and reconstruction performance of these models on various object types.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset