# Deep Geometry Post-Processing for Decompressed Point Clouds

arXiv: https://arxiv.org/abs/2204.13952 · HTML: https://mlsanity.com/paper/2204.13952/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 20 references that are in the map.
- First posted on arXiv 29 Apr 2022.

## Builds on (most cited first, 3 of 3)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Learned Point Cloud Geometry Compression](https://mlsanity.com/paper/1909.12037/) (2019)
- [Improved Deep Point Cloud Geometry Compression](https://mlsanity.com/paper/2006.09043/) (2020)

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

- [Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression](https://mlsanity.com/paper/2402.11250/) (2024)
- [UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Clouds](https://mlsanity.com/paper/2510.23009/) (2025)
- [Overview and Comparison of AVS Point Cloud Compression Standard](https://mlsanity.com/paper/2602.08613/) (2026)
- [Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression](https://mlsanity.com/paper/2508.01633/) (2025)
- [DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds](https://mlsanity.com/paper/2603.26183/) (2026)

## Abstract (arXiv)

Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission. However, distortions can be introduced into the decompressed point clouds due to quantization. In this paper, we propose a novel learning-based post-processing method to enhance the decompressed point clouds. Specifically, a voxelized point cloud is first divided into small cubes. Then, a 3D convolutional network is proposed to predict the occupancy probability for each location of a cube. We leverage both local and global contexts by generating multi-scale probabilities. These probabilities are progressively summed to predict the results in a coarse-to-fine manner. Finally, we obtain the geometry-refined point clouds based on the predicted probabilities. Different from previous methods, we deal with decompressed point clouds with huge variety of distortions using a single model. Experimental results show that the proposed method can significantly improve the quality of the decompressed point clouds, achieving 9.30dB BDPSNR gain on three representative datasets on average.