mlsanityData to 14 Oct 2026

3DAC: Learning Attribute Compression for Point Clouds

arXiv 2203.09931 ↗First posted 17 Mar 2022cs.CV eess.IVcited by 22

Not on the map. Why?

Abstract (arXiv)

We study the problem of attribute compression for large-scale unstructured 3D point clouds. Through an in-depth exploration of the relationships between different encoding steps and different attribute channels, we introduce a deep compression network, termed 3DAC, to explicitly compress the attributes of 3D point clouds and reduce storage usage in this paper. Specifically, the point cloud attributes such as color and reflectance are firstly converted to transform coefficients. We then propose a deep entropy model to model the probabilities of these coefficients by considering information hidden in attribute transforms and previous encoded attributes. Finally, the estimated probabilities are used to further compress these transform coefficients to a final attributes bitstream. Extensive experiments conducted on both indoor and outdoor large-scale open point cloud datasets, including ScanNet and SemanticKITTI, demonstrated the superior compression rates and reconstruction quality of the proposed 3DAC.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 26 of its 62 references that are in the map. First posted on arXiv 17 Mar 2022.

Builds on

26 of 62 references.

References · 26

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  4. 2018Variational image compression with a scale hyperpriorcited by 935
  5. 2016End-to-end Optimized Image Compressioncited by 696
  6. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  7. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 242
  8. 2021Checkerboard Context Model for Efficient Learned Image Compressioncited by 202
  9. 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
  10. 2020Multiscale Point Cloud Geometry Compressioncited by 74
  11. 2020OctSqueeze: Octree-Structured Entropy Model for LiDAR Compressioncited by 73
  12. 2021VoxelContext-Net: An Octree based Framework for Point Cloud Compressioncited by 61
14 more
  1. 2020Inferring Point Cloud Quality via Graph Similaritycited by 58
  2. 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
  3. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  4. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 50
  5. 2020Improved Deep Point Cloud Geometry Compressioncited by 43
  6. 2020MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Modelscited by 42
  7. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 39
  8. 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
  9. 2021Learning Scalable ℓ_∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compressioncited by 16
  10. 2020Folding-based compression of point cloud attributescited by 14
  11. 2017Attribute Compression of 3D Point Clouds Using Laplacian Sparsity Optimized Graph Transformcited by 12
  12. 2020Region adaptive graph fourier transform for 3d point cloudscited by 8
  13. 2018Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Predictioncited by 5
  14. 2021Multi-resolution intra-predictive coding of 3D point cloud attributescited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 10; 2025: 5; 2026: 5.

22 papers.

Sort:

By area:

  1. 2024MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformationcited by 56
  2. 2024SPAC: Sampling-based Progressive Attribute Compression for Dense Point Cloudscited by 11
  3. 2022CARNet:Compression Artifact Reduction for Point Cloud Attributecited by 6
  4. 2025Feed-Forward 3D Gaussian Splatting Compression with Long-Context Modelingcited by 6
  5. 2024Enhancing context models for point cloud geometry compression with context feature residuals and multi-losscited by 5
  6. 20243D Point Cloud Network Pruning: When Some Weights Do not Mattercited by 3
  7. 20224DAC: Learning Attribute Compression for Dynamic Point Cloudscited by 2
  8. 2024Efficient and Generic Point Model for Lossless Point Cloud Attribute Compressioncited by 2
  9. 2024Bits-to-Photon: End-to-End Learned Scalable Point Cloud Compression for Direct Renderingcited by 2
  10. 2026DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compressioncited by 2
  11. 2024Learned Compression of Point Cloud Geometry and Attributes in a Single Model through Multimodal Rate-Controlcited by 1
  12. 2024Att2CPC: Attention-Guided Lossy Attribute Compression of Point Cloudscited by 1
10 more
  1. 2024U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generationcited by 1
  2. 2024Implicit Neural Compression of Point Cloudscited by 1
  3. 2025Deep-JGAC: End-to-End Deep Joint Geometry and Attribute Compression for Dense Colored Point Cloudscited by 1
  4. 2025Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Codingcited by 1
  5. 2025UGAE: Unified Geometry and Attribute Enhancement for G-PCC Compressed Point Cloudscited by 1
  6. 2026DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compressioncited by 1
  7. 2025VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distributioncited by 0
  8. 2026MesonGS++: Post-training Compression of 3D Gaussian Splatting with Hyperparameter Searchingcited by 0
  9. 2026Proteus: A Truncation-Robust Entropy Model for Progressive LiDAR Compressioncited by 0
  10. 2026Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compressioncited by 0