# Neural Network Modeling of Probabilities for Coding the Octree Representation of Point Clouds

arXiv: https://arxiv.org/abs/2106.06482 · HTML: https://mlsanity.com/paper/2106.06482/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 10 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning-based lossless compression of 3D point cloud geometry](https://mlsanity.com/paper/2011.14700/) (2020)
- [Multiscale deep context modeling for lossless point cloud geometry compression](https://mlsanity.com/paper/2104.09859/) (2021)
- [Refining the bounding volumes for lossless compression of voxelized point clouds geometry](https://mlsanity.com/paper/2106.00828/) (2021)

## Built on by (most cited first, 4 of 4)

- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [LLM-PCGC: Large Language Model-based Point Cloud Geometry Compression](https://mlsanity.com/paper/2408.08682/) (2024)
- [Lossless Compression of Point Cloud Sequences Using Sequence Optimized CNN Models](https://mlsanity.com/paper/2206.01297/) (2022)

## Abstract (arXiv)

This paper describes a novel lossless point cloud compression algorithm that uses a neural network for estimating the coding probabilities for the occupancy status of voxels, depending on wide three dimensional contexts around the voxel to be encoded. The point cloud is represented as an octree, with each resolution layer being sequentially encoded and decoded using arithmetic coding, starting from the lowest resolution, until the final resolution is reached. The occupancy probability of each voxel of the splitting pattern at each node of the octree is modeled by a neural network, having at its input the already encoded occupancy status of several octree nodes (belonging to the past and current resolutions), corresponding to a 3D context surrounding the node to be encoded. The algorithm has a fast and a slow version, the fast version selecting differently several voxels of the context, which allows an increased parallelization by sending larger batches of templates to be estimated by the neural network, at both encoder and decoder. The proposed algorithms yield state-of-the-art results on benchmark datasets. The implementation will be made available at https://github.com/marmus12/nnctx