ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2304.00335
21
4

Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention

1 April 2023
Tam Thuc Do
P. Chou
Gene Cheung
    3DPC
ArXivPDFHTML
Abstract

We study 3D point cloud attribute compression using a volumetric approach: given a target volumetric attribute function f:R3→Rf : \mathbb{R}^3 \rightarrow \mathbb{R}f:R3→R, we quantize and encode parameter vector θ\thetaθ that characterizes fff at the encoder, for reconstruction fθ^(x)f_{\hat{\theta}}(\mathbf{x})fθ^​(x) at known 3D points x\mathbf{x}x's at the decoder. Extending a previous work Region Adaptive Hierarchical Transform (RAHT) that employs piecewise constant functions to span a nested sequence of function spaces, we propose a feedforward linear network that implements higher-order B-spline bases spanning function spaces without eigen-decomposition. Feedforward network architecture means that the system is amenable to end-to-end neural learning. The key to our network is space-varying convolution, similar to a graph operator, whose weights are computed from the known 3D geometry for normalization. We show that the number of layers in the normalization at the encoder is equivalent to the number of terms in a matrix inverse Taylor series. Experimental results on real-world 3D point clouds show up to 2-3 dB gain over RAHT in energy compaction and 20-30% bitrate reduction.

View on arXiv
Comments on this paper