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

TL;DR

SEDD-PCC introduces a unified encoder and dual decoder framework for end-to-end lossy point cloud compression, effectively sharing features between geometry and attributes to improve efficiency and performance.

Contribution

It proposes a novel single encoder-dual decoder architecture with knowledge distillation for joint geometry and attribute compression, reducing complexity and enhancing coding efficiency.

Findings

Competitive performance against rule-based methods

Effective feature sharing improves compression efficiency

Knowledge distillation enhances feature representation

Abstract

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.