# SEDD-PCC: A Single Encoder-Dual Decoder Framework For End-To-End Learned Point Cloud Compression

arXiv: https://arxiv.org/abs/2505.16709 · HTML: https://mlsanity.com/paper/2505.16709/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 29 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 10 of 10)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (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)
- [Multiscale Point Cloud Geometry Compression](https://mlsanity.com/paper/2011.03799/) (2020)
- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://mlsanity.com/paper/2111.10633/) (2021)
- [Sparse Tensor-based Point Cloud Attribute Compression](https://mlsanity.com/paper/2204.01023/) (2022)
- [GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression](https://mlsanity.com/paper/2209.04401/) (2022)
- [SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds](https://mlsanity.com/paper/2409.10293/) (2024)
- [The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machine](https://mlsanity.com/paper/2409.08130/) (2024)
- [Quality Analysis of the Coding Bitrate Tradeoff Between Geometry and Attributes for Colored Point Clouds](https://mlsanity.com/paper/2410.21613/) (2024)

## Abstract (arXiv)

To encode point clouds containing both geometry and attributes, most learning-based compression schemes treat geometry and attribute coding separately, employing distinct encoders and decoders. This not only increases computational complexity but also fails to fully exploit shared features between geometry and attributes. To address this limitation, we propose SEDD-PCC, an end-to-end learning-based framework for lossy point cloud compression that jointly compresses geometry and attributes. SEDD-PCC employs a single encoder to extract shared geometric and attribute features into a unified latent space, followed by dual specialized decoders that sequentially reconstruct geometry and attributes. Additionally, we incorporate knowledge distillation to enhance feature representation learning from a teacher model, further improving coding efficiency. With its simple yet effective design, SEDD-PCC provides an efficient and practical solution for point cloud compression. Comparative evaluations against both rule-based and learning-based methods demonstrate its competitive performance, highlighting SEDD-PCC as a promising AI-driven compression approach.