# Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss

arXiv: https://arxiv.org/abs/2407.08520 · HTML: https://mlsanity.com/paper/2407.08520/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 40 references that are in the map.
- First posted on arXiv 11 Jul 2024.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Fine-grained Image Similarity with Deep Ranking](https://mlsanity.com/paper/1404.4661/) (2014)
- [Practical Full Resolution Learned Lossless Image Compression](https://mlsanity.com/paper/1811.12817/) (2018)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression](https://mlsanity.com/paper/2005.07178/) (2020)
- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [VoxelContext-Net: An Octree based Framework for Point Cloud Compression](https://mlsanity.com/paper/2105.02158/) (2021)
- [Learned Point Cloud Geometry Compression](https://mlsanity.com/paper/1909.12037/) (2019)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Learning Convolutional Transforms for Lossy Point Cloud Geometry Compression](https://mlsanity.com/paper/1903.08548/) (2019)
- [MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models](https://mlsanity.com/paper/2011.07590/) (2020)
- [Learning-based lossless compression of 3D point cloud geometry](https://mlsanity.com/paper/2011.14700/) (2020)
- [Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model](https://mlsanity.com/paper/2303.06519/) (2023)
- [3DAC: Learning Attribute Compression for Point Clouds](https://mlsanity.com/paper/2203.09931/) (2022)
- [Multiscale deep context modeling for lossless point cloud geometry compression](https://mlsanity.com/paper/2104.09859/) (2021)
- [A Comprehensive Study and Comparison of Core Technologies for MPEG 3D Point Cloud Compression](https://mlsanity.com/paper/1912.09674/) (2019)
- [Point Cloud Compression with Sibling Context and Surface Priors](https://mlsanity.com/paper/2205.00760/) (2022)
- [Multiscale Latent-Guided Entropy Model for LiDAR Point Cloud Compression](https://mlsanity.com/paper/2209.12512/) (2022)

## Built on by (most cited first, 5 of 5)

- [SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds](https://mlsanity.com/paper/2409.10293/) (2024)
- [DiffCom: Decoupled Sparse Priors Guided Diffusion Compression for Point Clouds](https://mlsanity.com/paper/2411.13860/) (2024)
- [Deep-JGAC: End-to-End Deep Joint Geometry and Attribute Compression for Dense Colored Point Clouds](https://mlsanity.com/paper/2502.17939/) (2025)
- [UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds](https://mlsanity.com/paper/2510.23009/) (2025)
- [Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression](https://mlsanity.com/paper/2605.18006/) (2026)

## Abstract (arXiv)

In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the probability distribution predicted by the context model as the loss function. However, this approach has two main weaknesses. First, the differences between contexts of different nodes are not significant, making it difficult for the context model to accurately predict the probability distribution of node occupancy. Second, as the one-hot encoding is not the actual probability distribution of node occupancy, the cross-entropy loss function is inaccurate. To address these problems, we propose a general structure that can enhance existing context models. We introduce the context feature residuals into the context model to amplify the differences between contexts. We also add a multi-layer perception branch, that uses the mean squared error between its output and node occupancy as a loss function to provide accurate gradients in backpropagation. We validate our method by showing that it can improve the performance of an octree-based model (OctAttention) and a voxel-based model (VoxelDNN) on the object point cloud datasets MPEG 8i and MVUB, as well as the LiDAR point cloud dataset SemanticKITTI.