mlsanityData to 14 Oct 2026

LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks

arXiv 2111.08988 ↗First posted 17 Nov 2021cs.GR cs.LG eess.IVcited by 19

Not on the map. Why?

Abstract (arXiv)

We consider the attributes of a point cloud as samples of a vector-valued volumetric function at discrete positions. To compress the attributes given the positions, we compress the parameters of the volumetric function. We model the volumetric function by tiling space into blocks, and representing the function over each block by shifts of a coordinate-based, or implicit, neural network. Inputs to the network include both spatial coordinates and a latent vector per block. We represent the latent vectors using coefficients of the region-adaptive hierarchical transform (RAHT) used in the MPEG geometry-based point cloud codec G-PCC. The coefficients, which are highly compressible, are rate-distortion optimized by back-propagation through a rate-distortion Lagrangian loss in an auto-decoder configuration. The result outperforms RAHT by 2--4 dB. This is the first work to compress volumetric functions represented by local coordinate-based neural networks. As such, we expect it to be applicable beyond point clouds, for example to compression of high-resolution neural radiance fields.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 61 of its 109 references that are in the map. First posted on arXiv 17 Nov 2021.

Builds on

61 of 109 references.

References · 61

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  8. 2018Variational image compression with a scale hyperpriorcited by 935
  9. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  10. 2016End-to-end Optimized Image Compressioncited by 696
  11. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  12. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
38 more
  1. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  2. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  3. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  4. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
  5. 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 443
  6. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  7. 2020High-Fidelity Generative Image Compressioncited by 338
  8. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
  9. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  10. 2016Full Resolution Image Compression with Recurrent Neural Networkscited by 175
  11. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 173
  12. 2018Training Deep Neural Networks with 8-bit Floating Point Numberscited by 164
  13. 2018Scalable Methods for 8-bit Training of Neural Networkscited by 142
  14. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  15. 2020Nonlinear Transform Codingcited by 136
  16. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  17. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  18. 2021Unsupervised Discovery of Object Radiance Fieldscited by 101
  19. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  20. 2019And the Bit Goes Down: Revisiting the Quantization of Neural Networkscited by 78
  21. 2016End-to-end optimization of nonlinear transform codes for perceptual qualitycited by 73
  22. 2020Causal Contextual Prediction for Learned Image Compressioncited by 73
  23. 2021ACORN: Adaptive Coordinate Networks for Neural Scene Representationcited by 65
  24. 2020Universally Quantized Neural Compressioncited by 64
  25. 2020Learning End-to-End Lossy Image Compression: A Benchmarkcited by 60
  26. 2019Learning Convolutional Transforms for Lossy Point Cloud Geometry Compressioncited by 54
  27. 2021Seeing Implicit Neural Representations as Fourier Seriescited by 50
  28. 2020Improved Deep Point Cloud Geometry Compressioncited by 43
  29. 2021Rethinking Positional Encodingcited by 37
  30. 2019Scalable Model Compression by Entropy Penalized Reparameterizationcited by 31
  31. 2019Deep AutoEncoder-based Lossy Geometry Compression for Point Cloudscited by 29
  32. 2018Deep Neural Network Compression with Single and Multiple Level Quantizationcited by 27
  33. 2020Deep Implicit Volume Compressioncited by 26
  34. 2021An Information-Theoretic Justification for Model Pruningcited by 25
  35. 20213D Scene Compression through Entropy Penalized Neural Representation Functionscited by 23
  36. 2020The Rate-Distortion-Accuracy Tradeoff: JPEG Case Studycited by 22
  37. 2018Efficient Nonlinear Transforms for Lossy Image Compressioncited by 20
  38. 2015Graph-based compression of dynamic 3D point cloud sequencescited by 17

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 5; 2024: 3; 2025: 2; 2026: 4.

19 papers.

Sort:

By area:

  1. 2022Variable Bitrate Neural Fieldscited by 117
  2. 2022COIN++: Neural Compression Across Modalitiescited by 82
  3. 2023C3: High-performance and low-complexity neural compression from a single image or videocited by 55
  4. 2022Neural Fourier Filter Bankcited by 29
  5. 2023Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Modelcited by 25
  6. 2023Compact Neural Graphics Primitives with Learned Hash Probingcited by 19
  7. 2024Point Cloud Compression with Implicit Neural Representations: A Unified Frameworkcited by 6
  8. 2023Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attentioncited by 4
  9. 20224DAC: Learning Attribute Compression for Dynamic Point Cloudscited by 2
  10. 2023Learned Nonlinear Predictor for Critically Sampled 3D Point Cloud Attribute Compressioncited by 2
  11. 2024Efficient and Generic Point Model for Lossless Point Cloud Attribute Compressioncited by 2
  12. 2026DeepRAHT: Learning Predictive RAHT for Point Cloud Attribute Compressioncited by 2
7 more
  1. 2022Lossy Compression of Noisy Data for Private and Data-Efficient Learningcited by 1
  2. 2024Implicit Neural Compression of Point Cloudscited by 1
  3. 2025Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Codingcited by 1
  4. 2026Transforming harmonic coefficients for 3D splat compressioncited by 1
  5. 2025VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distributioncited by 0
  6. 2026HybridINR-PCGC: Hybrid Lossless Point Cloud Geometry Compression Bridging Pretrained Model and Implicit Neural Representationcited by 0
  7. 2026Transform-Aligned Learned Features for Lossy Point Cloud Attribute Compressioncited by 0