3DShapes

The '3DShapes' dataset is a synthetic benchmark that contains 3D shapes generated with varying factors of variation, used to evaluate the effectiveness of models in learning and disentangling these underlying generative factors.

Papers using 3DShapes (2)

Multiple Invertible and Partial-Equivariant Function for Latent Vector Transformation to Enhance Disentanglement in VAEs2025DOT-VAE: Disentangling One Factor at a Time2022