Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space

• URL: http://arxiv.org/abs/2504.14471v1
• Date: Sun, 20 Apr 2025 03:37:32 GMT
• Title: Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space
• Authors: Yichi Zhang, Qianqian Yang,
• Abstract summary: Implicit Neural Representations (INRs) have emerged as a powerful paradigm in deep learning.<n>We propose textbfPICO, an INR-based framework for static point cloud compression.<n>Our approach exhibits highly competitive results, with an average PCQM gain of $2.7 times 10-3$.
• Score: 10.056460330355193
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Implicit Neural Representations (INRs), also known as neural fields, have emerged as a powerful paradigm in deep learning, parameterizing continuous spatial fields using coordinate-based neural networks. In this paper, we propose \textbf{PICO}, an INR-based framework for static point cloud compression. Unlike prevailing encoder-decoder paradigms, we decompose the point cloud compression task into two separate stages: geometry compression and attribute compression, each with distinct INR optimization objectives. Inspired by Kolmogorov-Arnold Networks (KANs), we introduce a novel network architecture, \textbf{LeAFNet}, which leverages learnable activation functions in the latent space to better approximate the target signal's implicit function. By reformulating point cloud compression as neural parameter compression, we further improve compression efficiency through quantization and entropy coding. Experimental results demonstrate that \textbf{LeAFNet} outperforms conventional MLPs in INR-based point cloud compression. Furthermore, \textbf{PICO} achieves superior geometry compression performance compared to the current MPEG point cloud compression standard, yielding an average improvement of $4.92$ dB in D1 PSNR. In joint geometry and attribute compression, our approach exhibits highly competitive results, with an average PCQM gain of $2.7 \times 10^{-3}$.

Related papers

• Hierarchical Semantic Compression for Consistent Image Semantic Restoration [62.97519327310638]
  We propose a novel hierarchical semantic compression (HSC) framework that purely operates within intrinsic semantic spaces from generative models.<n> Experimental results demonstrate that the proposed HSC framework achieves the state-of-the-art performance on subjective quality and consistency for human vision.
  arXiv  Detail & Related papers  (2025-02-24T03:20:44Z)
• Implicit Neural Compression of Point Clouds [58.45774938982386]
  NeRC$textbf3$ is a novel point cloud compression framework leveraging implicit neural representations to handle both geometry and attributes.<n>For dynamic point clouds, 4D-NeRC$textbf3$ demonstrates superior geometry compression compared to state-of-the-art G-PCC and V-PCC standards.
  arXiv  Detail & Related papers  (2024-12-11T03:22:00Z)
• Point Cloud Compression with Bits-back Coding [32.9521748764196]
  This paper specializes in using a deep learning-based probabilistic model to estimate the Shannon's entropy of the point cloud information. Once the entropy of the point cloud dataset is estimated, we use the learned CVAE model to compress the geometric attributes of the point clouds. The novelty of our method with bits-back coding specializes in utilizing the learned latent variable model of the CVAE to compress the point cloud data.
  arXiv  Detail & Related papers  (2024-10-09T06:34:48Z)
• End-to-end learned Lossy Dynamic Point Cloud Attribute Compression [5.717288278431968]
  This study introduces an end-to-end learned dynamic lossy attribute coding approach. We employ a context model that leverage previous latent space in conjunction with an auto-regressive context model for encoding the latent tensor into a bitstream.
  arXiv  Detail & Related papers  (2024-08-20T09:06:59Z)
• Point Cloud Compression with Implicit Neural Representations: A Unified Framework [54.119415852585306]
  We present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. Our method exhibits high universality when contrasted with existing learning-based techniques.
  arXiv  Detail & Related papers  (2024-05-19T09:19:40Z)
• "Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach [49.744093838327615]
  We provide a novel compression approach to wide and fully-connected emphdeep neural nets. Experiments on both synthetic and real-world data are conducted to support the advantages of the proposed compression scheme.
  arXiv  Detail & Related papers  (2024-03-01T03:46:28Z)
• Towards Hardware-Specific Automatic Compression of Neural Networks [0.0]
  pruning and quantization are the major approaches to compress neural networks nowadays. Effective compression policies consider the influence of the specific hardware architecture on the used compression methods. We propose an algorithmic framework called Galen to search such policies using reinforcement learning utilizing pruning and quantization.
  arXiv  Detail & Related papers  (2022-12-15T13:34:02Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• DeepCompress: Efficient Point Cloud Geometry Compression [1.808877001896346]
  We propose a more efficient deep learning-based encoder architecture for point clouds compression. We show that incorporating the learned activation function from Efficient Neural Image Compression (CENIC) yields dramatic gains in efficiency and performance. Our proposed modifications outperform the baseline approaches by a small margin in terms of Bjontegard delta rate and PSNR values.
  arXiv  Detail & Related papers  (2021-06-02T23:18:11Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)

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.