# RocNet: Recursive Octree Network for Efficient 3D Deep Representation

arXiv: https://arxiv.org/abs/2008.03875 · HTML: https://mlsanity.com/paper/2008.03875/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Aug 2020.

## Built on by (most cited first, 1 of 1)

- [N-QGN: Navigation Map from a Monocular Camera using Quadtree Generating Networks](https://mlsanity.com/paper/2202.11982/) (2022)

## Abstract (arXiv)

We introduce a deep recursive octree network for the compression of 3D voxel data. 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 32, 64 and 128 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 three experiments: 3D shape classification, 3D shape reconstruction, and shape generation. 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.