Hierarchical Prior-based Super Resolution for Point Cloud Geometry Compression
This work addresses compression quality issues in point cloud geometry for applications like 3D media and virtual reality, representing an incremental improvement over standard methods.
The paper tackles the problem of noticeable distortions in reconstructed point clouds from G-PCC due to naive geometry quantization by proposing a hierarchical prior-based super resolution method, achieving substantial Bjontegaard-delta bitrate savings on the MPEG Cat1A dataset compared to existing G-PCC versions.
The Geometry-based Point Cloud Compression (G-PCC) has been developed by the Moving Picture Experts Group to compress point clouds. In its lossy mode, the reconstructed point cloud by G-PCC often suffers from noticeable distortions due to the naïve geometry quantization (i.e., grid downsampling). This paper proposes a hierarchical prior-based super resolution method for point cloud geometry compression. The content-dependent hierarchical prior is constructed at the encoder side, which enables coarse-to-fine super resolution of the point cloud geometry at the decoder side. A more accurate prior generally yields improved reconstruction performance, at the cost of increased bits required to encode this side information. With a proper balance between prior accuracy and bit consumption, the proposed method demonstrates substantial Bjontegaard-delta bitrate savings on the MPEG Cat1A dataset, surpassing the octree-based and trisoup-based G-PCC v14. We provide our implementations for reproducible research at https://github.com/lidq92/mpeg-pcc-tmc13.