SEDD-PCC: A Single Encoder-Dual Decoder Framework For End-To-End Learned Point Cloud Compression
This addresses the computational complexity and feature exploitation issues in point cloud compression for applications like 3D data processing, though it appears incremental as it builds on prior learning-based methods.
The paper tackles the problem of inefficient separate encoding for geometry and attributes in point cloud compression by proposing SEDD-PCC, an end-to-end framework that uses a single encoder and dual decoders to jointly compress them, achieving competitive performance in evaluations against existing methods.
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.