Score: 0

MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud Compression

Published: December 27, 2025 | arXiv ID: 2512.22463v1

By: Kai-Hsiang Hsieh , Monyneath Yim , Wen-Hsiao Peng and more

Potential Business Impact:

Makes 3D models smaller for faster sharing.

Business Areas:
Image Recognition Data and Analytics, Software

Joint compression of point cloud geometry and attributes is essential for efficient 3D data representation. Existing methods often rely on post-hoc recoloring procedures and manually tuned bitrate allocation between geometry and attribute bitstreams in inference, which hinders end-to-end optimization and increases system complexity. To overcome these limitations, we propose MEGA-PCC, a fully end-to-end, learning-based framework featuring two specialized models for joint compression. The main compression model employs a shared encoder that encodes both geometry and attribute information into a unified latent representation, followed by dual decoders that sequentially reconstruct geometry and then attributes. Complementing this, the Mamba-based Entropy Model (MEM) enhances entropy coding by capturing spatial and channel-wise correlations to improve probability estimation. Both models are built on the Mamba architecture to effectively model long-range dependencies and rich contextual features. By eliminating the need for recoloring and heuristic bitrate tuning, MEGA-PCC enables data-driven bitrate allocation during training and simplifies the overall pipeline. Extensive experiments demonstrate that MEGA-PCC achieves superior rate-distortion performance and runtime efficiency compared to both traditional and learning-based baselines, offering a powerful solution for AI-driven point cloud compression.

Country of Origin
🇹🇼 Taiwan, Province of China

Page Count
11 pages

Category
Electrical Engineering and Systems Science:
Image and Video Processing