Volumetric Attribute Compression for 3D Point Clouds using Feedforward Network with Geometric Attention
This work addresses compression efficiency for 3D point cloud data, which is incremental as it builds on prior RAHT methods with specific improvements.
The paper tackles 3D point cloud attribute compression by proposing a feedforward linear network with geometric attention, which replaces piecewise constant functions with higher-order B-spline bases and avoids eigen-decomposition. Experimental results show up to 2-3 dB gain in energy compaction and 20-30% bitrate reduction compared to the previous RAHT method.
We 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 $θ$ that characterizes $f$ at the encoder, for reconstruction $f_{\hatθ}(\mathbf{x})$ at known 3D points $\mathbf{x}$'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.