mlsanityData to 14 Oct 2026

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

arXiv 2512.22463 ↗First posted 27 Dec 2025eess.IV cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 32 of its 59 references that are in the map. First posted on arXiv 27 Dec 2025.

Builds on

32 of 59 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model23 Apr
  2. 2024Point Cloud Mamba: Point Cloud Learning via State Space Model1 Mar

Other references · 30

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2020Point Transformercited by 1,470
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  7. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  8. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  9. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  10. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  11. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  12. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
18 more
  1. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  2. 2020Multiscale Point Cloud Geometry Compressioncited by 74
  3. 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 73
  4. 2021Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compressioncited by 70
  5. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 61
  6. 2020Inferring Point Cloud Quality via Graph Similaritycited by 58
  7. 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
  8. 2023Super Sparse 3D Object Detectioncited by 32
  9. 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
  10. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  11. 2022Sparse Tensor-based Point Cloud Attribute Compressioncited by 25
  12. 2024TSC-PCAC: Voxel Transformer and Sparse Convolution Based Point Cloud Attribute Compression for 3D Broadcastingcited by 12
  13. 2024ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attentioncited by 11
  14. 2020Real-World Textured Things: a Repository of Textured Models Generated with Modern Photo-Reconstruction Toolscited by 10
  15. 2024The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machinecited by 9
  16. 2022Variable Rate Compression for Raw 3D Point Cloudscited by 4
  17. 2024PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Modelcited by 2
  18. 2025Deep-JGAC: End-to-End Deep Joint Geometry and Attribute Compression for Dense Colored Point Cloudscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SEDD-PCC: A Single Encoder-Dual Decoder Framework For End-To-End Learned Point Cloud Compression
  2. 2024Point Cloud Compression with Implicit Neural Representations: A Unified Framework
  3. 2024SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds
  4. 2024Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
  5. 2026Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compression
  6. 2021Attribute Artifacts Removal for Geometry-based Point Cloud Compression
  7. 2023Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compression
  8. 2024Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression