Deep Unrolling of Sparsity-Induced RDO for 3D Point Cloud Attribute Coding

arXiv:2509.08685v2 Announce Type: replace-cross Abstract: Given encoded 3D point cloud geometry available at the decoder, we study the problem of lossy attribute compression in a multi-resolution B-spline projection framework. A target continuous 3D attribute function is first projected onto a sequence of nested subspaces F^{(p)}{l_0} subseteq dots subseteq F^{(p)}{L}, where F^{(p)}_{l} 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_l^* are computed by variable-complexity unrolling of a rate-distortion (RD) optimization algorithm into a feed-forward network, where the rate term is the sparsity-promoting ell_1-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.

Source: arXiv cs.LG | 2026-07-16