Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning
This work addresses the need for high-fidelity point cloud upsampling in practical applications like 3D modeling and computer vision, offering an incremental improvement over prior methods by enhancing geometric accuracy.
The paper tackles the problem of arbitrary-scale point cloud upsampling, where existing methods struggle with low-fidelity geometry due to surface approximation challenges, and proposes PU-VoxelNet, which uses a voxel-based network with density-guided resampling and latent geometric-consistent learning to outperform state-of-the-art approaches in both fixed and arbitrary-scale upsampling.
Recently, arbitrary-scale point cloud upsampling mechanism became increasingly popular due to its efficiency and convenience for practical applications. To achieve this, most previous approaches formulate it as a problem of surface approximation and employ point-based networks to learn surface representations. However, learning surfaces from sparse point clouds is more challenging, and thus they often suffer from the low-fidelity geometry approximation. To address it, we propose an arbitrary-scale Point cloud Upsampling framework using Voxel-based Network (\textbf{PU-VoxelNet}). Thanks to the completeness and regularity inherited from the voxel representation, voxel-based networks are capable of providing predefined grid space to approximate 3D surface, and an arbitrary number of points can be reconstructed according to the predicted density distribution within each grid cell. However, we investigate the inaccurate grid sampling caused by imprecise density predictions. To address this issue, a density-guided grid resampling method is developed to generate high-fidelity points while effectively avoiding sampling outliers. Further, to improve the fine-grained details, we present an auxiliary training supervision to enforce the latent geometric consistency among local surface patches. Extensive experiments indicate the proposed approach outperforms the state-of-the-art approaches not only in terms of fixed upsampling rates but also for arbitrary-scale upsampling.