Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression

• URL: http://arxiv.org/abs/2508.01633v1
• Date: Sun, 03 Aug 2025 07:40:42 GMT
• Title: Rate-distortion Optimized Point Cloud Preprocessing for Geometry-based Point Cloud Compression
• Authors: Wanhao Ma, Wei Zhang, Shuai Wan, Fuzheng Yang,
• Abstract summary: Geometry-based point cloud compression (G-PCC) underperforms compared to recent deep learning-based PCC methods.<n>We propose a novel preprocessing framework that integrates a compression-oriented voxelization network with a differentiable G-PCC surrogate model.<n>Experiments demonstrate a 38.84% average BD-rate reduction over G-PCC.
• Score: 13.926314302842073
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Geometry-based point cloud compression (G-PCC), an international standard designed by MPEG, provides a generic framework for compressing diverse types of point clouds while ensuring interoperability across applications and devices. However, G-PCC underperforms compared to recent deep learning-based PCC methods despite its lower computational power consumption. To enhance the efficiency of G-PCC without sacrificing its interoperability or computational flexibility, we propose a novel preprocessing framework that integrates a compression-oriented voxelization network with a differentiable G-PCC surrogate model, jointly optimized in the training phase. The surrogate model mimics the rate-distortion behaviour of the non-differentiable G-PCC codec, enabling end-to-end gradient propagation. The versatile voxelization network adaptively transforms input point clouds using learning-based voxelization and effectively manipulates point clouds via global scaling, fine-grained pruning, and point-level editing for rate-distortion trade-offs. During inference, only the lightweight voxelization network is appended to the G-PCC encoder, requiring no modifications to the decoder, thus introducing no computational overhead for end users. Extensive experiments demonstrate a 38.84% average BD-rate reduction over G-PCC. By bridging classical codecs with deep learning, this work offers a practical pathway to enhance legacy compression standards while preserving their backward compatibility, making it ideal for real-world deployment.

Related papers

• High Efficiency Wiener Filter-based Point Cloud Quality Enhancement for MPEG G-PCC [23.8642501868336]
  Point clouds directly record the geometry and attributes of scenes or objects by a large number of points.<n> geometry-based point cloud compression (G-PCC) standard for both static and dynamic point clouds.<n>We propose a high efficiency Wiener filter that can be integrated into the encoder and decoder pipeline of G-PCC.
  arXiv  Detail & Related papers  (2025-03-21T18:24:58Z)
• PCE-GAN: A Generative Adversarial Network for Point Cloud Attribute Quality Enhancement based on Optimal Transport [56.56430888985025]
  We propose a generative adversarial network for point cloud quality enhancement (PCE-GAN)<n>The generator consists of a local feature extraction (LFE) unit, a global spatial correlation (GSC) unit and a feature squeeze unit.<n>The discriminator computes the deviation between the probability distributions of the enhanced point cloud and the original point cloud, guiding the generator to achieve high quality reconstruction.
  arXiv  Detail & Related papers  (2025-02-26T07:34:33Z)
• Rate-Distortion Optimized Skip Coding of Region Adaptive Hierarchical Transform Coefficients for MPEG G-PCC [13.122745400640305]
  Three-dimensional (3D) point clouds are becoming more and more popular for representing 3D objects and scenes.<n>To tackle this challenge, the Moving Picture Experts Group is actively developing the Geometry-based Point Cloud Compression (G-PCC) standard.<n>We propose an adaptive skip method for RAHT, which adaptively determines whether to encode the residuals of the last several layers or not.
  arXiv  Detail & Related papers  (2024-12-07T07:43:44Z)
• SPAC: Sampling-based Progressive Attribute Compression for Dense Point Clouds [51.313922535437726]
  We propose an end-to-end compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module with geometry assistance, and a global hyperprior entropy model.
  arXiv  Detail & Related papers  (2024-09-16T13:59:43Z)
• The JPEG Pleno Learning-based Point Cloud Coding Standard: Serving Man and Machine [49.16996486119006]
  Deep learning has emerged as a powerful tool in point cloud coding.<n> JPEG has recently finalized the JPEG Pleno Learning-based Point Cloud Coding standard.<n>This paper provides a complete technical description of the JPEG PCC standard.
  arXiv  Detail & Related papers  (2024-09-12T15:20:23Z)
• Efficient and Generic Point Model for Lossless Point Cloud Attribute Compression [28.316347464011056]
  PoLoPCAC is an efficient and generic PCAC method that achieves high compression efficiency and strong generalizability simultaneously. Our method can be instantly deployed once trained on a Synthetic 2k-ShapeNet dataset. Experiments show that our method can enjoy continuous bit-rate reduction over the latest G-PCCv23 on various datasets.
  arXiv  Detail & Related papers  (2024-04-10T11:40:02Z)
• Quantize Once, Train Fast: Allreduce-Compatible Compression with Provable Guarantees [53.950234267704]
  We introduce Global-QSGD, an All-reduce gradient-compatible quantization method.<n>We show that it accelerates distributed training by up to 3.51% over baseline quantization methods.
  arXiv  Detail & Related papers  (2023-05-29T21:32:15Z)
• Dynamic Point Cloud Geometry Compression Using Multiscale Inter Conditional Coding [27.013814232906817]
  This work extends the Multiscale Sparse Representation (MSR) framework developed for Point Cloud Geometry Compression (PCGC) to support the dynamic PCGC. The reconstruction of the preceding Point Cloud Geometry (PCG) frame is progressively downscaled to generate multiscale temporal priors.
  arXiv  Detail & Related papers  (2023-01-28T11:34:06Z)
• L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep Learning [24.712888488317816]
  We provide a framework for adapting the degree of compression across the model's layers dynamically during training. Our framework, called L-GreCo, is based on an adaptive algorithm, which automatically picks the optimal compression parameters for model layers.
  arXiv  Detail & Related papers  (2022-10-31T14:37:41Z)
• Neural JPEG: End-to-End Image Compression Leveraging a Standard JPEG Encoder-Decoder [73.48927855855219]
  We propose a system that learns to improve the encoding performance by enhancing its internal neural representations on both the encoder and decoder ends. Experiments demonstrate that our approach successfully improves the rate-distortion performance over JPEG across various quality metrics.
  arXiv  Detail & Related papers  (2022-01-27T20:20:03Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.