Temporal Filtering for Region Adaptive Hierarchical Transform in Geometric Point Cloud Compression
Bharath Vishwanath, Yingzhan Xu, Wenyi Wang, Kai Zhang, Li Zhang · 2023
Dynamic point cloud compression is critical for the success of immersive multimedia applications and autonomous driving. For attribute compression in geometric point cloud compression (G-PCC), Region Adaptive Hierarchical Transform (RAHT) is the preferred coding method. Recently, inter-prediction was introduced for RAHT in G-PCC. In inter-RAHT, the transform coefficients of the top layers (low frequency coefficients) are predicted by a simple copy of the transform coefficients from the reference frame. Such a prediction assumes reference and current RAHT layers are perfectly correlated, which is barely true. To address this, the paper introduces a temporal filtering mechanism for RAHT. Specifically, we scale the reference layer by a filtering coefficient. Different filtering coefficients are designed for different RAHT layers, thereby emulating a low-pass filter. Experiments show an average 2% bit-rate savings over G-PCC test model tmc13-v22 with negligible increase in complexity. The method has been adopted to the second version of G-PCC.