Learning to Generate 3D Shapes with Generative Cellular Automata
This work addresses the problem of efficient and high-quality 3D shape generation for computer graphics and AI applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles 3D shape generation by proposing Generative Cellular Automata, a model that uses Markov chains and cellular automata rules to progressively generate shapes, focusing on sparse voxels to reduce computational complexity. It achieves competitive performance in shape completion and generation tasks, as demonstrated in experiments.
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.