# D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction

arXiv: https://arxiv.org/abs/2205.01135 · HTML: https://mlsanity.com/paper/2205.01135/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 2 May 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [End-to-end Optimized Image Compression](https://mlsanity.com/paper/1611.01704/) (2016)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [FVC: A New Framework towards Deep Video Compression in Feature Space](https://mlsanity.com/paper/2105.09600/) (2021)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [Learned Point Cloud Geometry Compression](https://mlsanity.com/paper/1909.12037/) (2019)
- [Hierarchical Attention Learning of Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/2010.05762/) (2020)
- [Learning-based lossless compression of 3D point cloud geometry](https://mlsanity.com/paper/2011.14700/) (2020)
- [Residual 3D Scene Flow Learning with Context-Aware Feature Extraction](https://mlsanity.com/paper/2109.04685/) (2021)

## Built on by (most cited first, 18 of 18)

- [MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment](https://mlsanity.com/paper/2209.00244/) (2022)
- [LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM](https://mlsanity.com/paper/2404.18203/) (2024)
- [Geometric Prior Based Deep Human Point Cloud Geometry Compression](https://mlsanity.com/paper/2305.01309/) (2023)
- [ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2505.08196/) (2025)
- [Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding](https://mlsanity.com/paper/2301.12165/) (2023)
- [Learning Dynamic Point Cloud Compression via Hierarchical Inter-frame Block Matching](https://mlsanity.com/paper/2305.05356/) (2023)
- [Learning Neural Volumetric Field for Point Cloud Geometry Compression](https://mlsanity.com/paper/2212.05589/) (2022)
- [U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generation](https://mlsanity.com/paper/2411.14501/) (2024)
- [Implicit Neural Compression of Point Clouds](https://mlsanity.com/paper/2412.10433/) (2024)
- [DPCD: A Quality Assessment Database for Dynamic Point Clouds](https://mlsanity.com/paper/2505.12431/) (2025)
- [Point Cloud Compression and Objective Quality Assessment: A Survey](https://mlsanity.com/paper/2506.22902/) (2025)
- [AnyPcc: Compressing Any Point Cloud with a Single Universal Model](https://mlsanity.com/paper/2510.20331/) (2025)
- [Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression](https://mlsanity.com/paper/2509.14591/) (2025)
- [SurfelSoup: Learned Point Cloud Geometry Compression With a Probablistic SurfelTree Representation](https://mlsanity.com/paper/2602.00186/) (2026)
- [DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds](https://mlsanity.com/paper/2603.26183/) (2026)
- [LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2603.28431/) (2026)
- [Proteus: A Truncation-Robust Entropy Model for Progressive LiDAR Compression](https://mlsanity.com/paper/2608.00687/) (2026)
- [Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors](https://mlsanity.com/paper/2609.33969/) (2026)

## Abstract (arXiv)

The non-uniformly distributed nature of the 3D dynamic point cloud (DPC) brings significant challenges to its high-efficient inter-frame compression. This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space. In the proposed D-DPCC network, we design a it Multi-scale Motion Fusion (MMF) module to accurately estimate the 3D optical flow between the feature representations of adjacent point cloud frames. Specifically, we utilize a 3D sparse convolution-based encoder to obtain the latent representation for motion estimation in the feature space and introduce the proposed MMF module for fused 3D motion embedding. Besides, for motion compensation, we propose a 3D it Adaptively Weighted Interpolation (3DAWI) algorithm with a penalty coefficient to adaptively decrease the impact of distant neighbors. We compress the motion embedding and the residual with a lossy autoencoder-based network. To our knowledge, this paper is the first work proposing an end-to-end deep dynamic point cloud compression framework. The experimental result shows that the proposed D-DPCC framework achieves an average 76% BD-Rate (Bjontegaard Delta Rate) gains against state-of-the-art Video-based Point Cloud Compression (V-PCC) v13 in inter mode.