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

Simple item page
dc.contributor.advisorGene Cheung
dc.contributor.authorViet Ho Tam Thuc Do
dc.date.accessioned2023-08-04T15:12:34Z
dc.date.available2023-08-04T15:12:34Z
dc.date.issued2023-08-04
dc.date.updated2023-08-04T15:12:34Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractWe study 3D point cloud attribute compression using a volumetric approach: given a target volumetric attribute function $f : \mathbb{R}^3 \rightarrow \mathbb{R}$, we quantize and encode parameter vector $\theta$ that characterizes $f$ at the encoder, for reconstruction $f_{\hat{\theta}}(\x)$ at known 3D points $\x$'s at the decoder, where $\hat{\theta}$ is a quantized version of $\theta$. 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\% in bitrate reduction.
dc.identifier.urihttps://hdl.handle.net/10315/41338
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectEngineering
dc.subjectComputer science
dc.subjectApplied mathematics
dc.subject.keywords3D point cloud compression
dc.subject.keywordsSignal Processing
dc.titleVolumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Thesis_-_DoTamThuc_-_219122134.pdf
Size:
2.9 MB
Format:
Adobe Portable Document Format
Download

Collections

ETD SWORD Deposit

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.