用生成式元胞自动机学习生成三维图形
Learning to Generate 3D Shapes with Generative Cellular Automata
摘要:
我们提出了一个概率三维生成模型,命名为生成元胞自动机,它能够产生多样化和高质量的形状。我们将形状生成过程制定为从马尔可夫链的过渡内核采样,其中采样链最终演变为学习分布的完整形状。过渡核采用元胞自动机的局部更新规则,通过利用三维形状的连通性和稀疏性,有效地减少了高分辨率三维网格空间中的搜索空间。我们的渐进式生成只关注稀疏的占用体素及其邻域,从而能够利用有表现力的稀疏卷积网络。我们提出了一种有效的训练方案,以获得局部齐次规则的生成式细胞自动机的序列是略有不同的采样链,但收敛到完整的形状在训练数据。大量的概率形状完成和形状生成的实验表明,我们的方法实现了竞争力的性能对最近的方法。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。