Abstract
We introduce a deep recursive octree network for general-purpose 3D voxel data processing. Our network compresses a voxel grid of any size down to a very small latent space in an autoencoder-like network. We show results for compressing 323, 643 and 1283 grids down to just 80 floats in the latent space. We demonstrate the effectiveness and efficiency of our proposed method on several publicly available datasets with four experiments: 3D shape classification, 3D shape reconstruction, shape generation and semantic segmentation. Experimental results show that our algorithm maintains accuracy while consuming less memory with shorter training times compared to existing methods, especially in 3D reconstruction tasks.