Learning to Generate 3D Shapes with Generative Cellular Automata

Abstract

We present a probabilistic 3D generative model, named Generative Cellular Automata, which is able to produce diverse and high quality shapes. We formulate the shape generation process as sampling from the transition kernel of a Markov chain, where the sampling chain eventually evolves to the full shape of the learned distribution. The transition kernel employs the local update rules of cellular automata, effectively reducing the search space in a high-resolution 3D grid space by exploiting the connectivity and sparsity of 3D shapes. Our progressive generation only focuses on the sparse set of occupied voxels and their neighborhood, thus enabling the utilization of an expressive sparse convolutional network. We propose an effective training scheme to obtain the local homogeneous rule of generative cellular automata with sequences that are slightly different from the sampling chain but converge to the full shapes in the training data. Extensive experiments on probabilistic shape completion and shape generation demonstrate that our method achieves competitive performance against recent methods.

arXiv commentICLR 2021

References in corpus (9)

• Neural Discrete Representation Learning
• Conditional Image Generation with PixelCNN Decoders
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
• Learning Representations and Generative Models for 3D Point Clouds
• How (not) to Train your Generative Model: Scheduled Sampling, Likelihood, Adversary?
• PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
• Improved Adversarial Systems for 3D Object Generation and Reconstruction
• Learning to Generate Samples from Noise through Infusion Training