Refining 3D Point Cloud Normal Estimation via Sample Selection
This work addresses robustness issues in normal estimation for 3D geometric processing, though it appears incremental as it builds upon existing methods.
The paper tackles the problem of improving robustness in 3D point cloud normal estimation by enhancing existing neural network models with global information, constraint mechanisms, and a confidence-based sample selection strategy, achieving state-of-the-art performance on oriented and non-oriented tasks.
In recent years, point cloud normal estimation, as a classical and foundational algorithm, has garnered extensive attention in the field of 3D geometric processing. Despite the remarkable performance achieved by current Neural Network-based methods, their robustness is still influenced by the quality of training data and the models' performance. In this study, we designed a fundamental framework for normal estimation, enhancing existing model through the incorporation of global information and various constraint mechanisms. Additionally, we employed a confidence-based strategy to select the reasonable samples for fair and robust network training. The introduced sample confidence can be integrated into the loss function to balance the influence of different samples on model training. Finally, we utilized existing orientation methods to correct estimated non-oriented normals, achieving state-of-the-art performance in both oriented and non-oriented tasks. Extensive experimental results demonstrate that our method works well on the widely used benchmarks.