Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 42579590.
- Also identified by DOI 10.1109/TIP.2026.3718443.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
We study the problem of lossy attribute compression, given encoded 3D point cloud geometry available at the decoder, in a multi-resolution B-spline projection framework. A target continuous 3D attribute function is first projected onto a sequence of nested subspaces F<sup>(p)</sup> <sub>l0</sub> ⊆ · · · ⊆ F<sup>(p)</sup> <sub>L</sub> , where F<sup>(p)</sup> <sub>l</sub> is a family of functions spanned by a B-spline basis function of order p at a chosen scale and its integer shifts. The projected low-pass coefficients F<sup>∗</sup> <sub>l</sub> are computed via variable-complexity unrolling of a rate-distortion (RD) optimization algorithm into a feed-forward network, where the rate term is the sparsity-promoting ℓ<sub>1</sub>-norm. Thus, the projection operation is end-to-end differentiable. For a chosen coarse-to-fine predictor, the coefficients are then adjusted to account for the prediction from a lower-resolution to a higher-resolution, which is also optimized in a data-driven manner.