# Hierarchical Attention Networks for Lossless Point Cloud Attribute Compression

arXiv: https://arxiv.org/abs/2504.00481 · HTML: https://mlsanity.com/paper/2504.00481/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Builds on (most cited first, 6 of 6)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [Lossless Point Cloud Attribute Compression Using Cross-scale, Cross-group, and Cross-color Prediction](https://mlsanity.com/paper/2303.12917/) (2023)
- [Point Cloud Attribute Compression via Successive Subspace Graph Transform](https://mlsanity.com/paper/2010.15302/) (2020)

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

- [Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression](https://mlsanity.com/paper/2609.34834/) (2026)

## Abstract (arXiv)

In this paper, we propose a deep hierarchical attention context model for lossless attribute compression of point clouds, leveraging a multi-resolution spatial structure and residual learning. A simple and effective Level of Detail (LoD) structure is introduced to yield a coarse-to-fine representation. To enhance efficiency, points within the same refinement level are encoded in parallel, sharing a common context point group. By hierarchically aggregating information from neighboring points, our attention model learns contextual dependencies across varying scales and densities, enabling comprehensive feature extraction. We also adopt normalization for position coordinates and attributes to achieve scale-invariant compression. Additionally, we segment the point cloud into multiple slices to facilitate parallel processing, further optimizing time complexity. Experimental results demonstrate that the proposed method offers better coding performance than the latest G-PCC for color and reflectance attributes while maintaining more efficient encoding and decoding runtimes.