Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis and generation. In this paper, we propose a normal refinement network, called Refine-Net, to predict accurate normals for noisy point clouds. Traditional normal estimation wisdom heavily depends on priors such as surface shapes or noise distributions, while learning-based solutions settle for single types of hand-crafted features. Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations. To this end, several feature modules are developed and incorporated into Refine-Net by a novel connection module. Besides the overall network architecture of Refine-Net, we propose a new multi-scale fitting patch selection scheme for the initial normal estimation, by absorbing geometry domain knowledge. Also, Refine-Net is a generic normal estimation framework: 1) point normals obtained from other methods can be further refined, and 2) any feature module related to the surface geometric structures can be potentially integrated into the framework. Qualitative and quantitative evaluations demonstrate the clear superiority of Refine-Net over the state-of-the-arts on both synthetic and real-scanned datasets.
|Number of pages||18|
|Journal||IEEE Transactions on Pattern Analysis and Machine Intelligence|
|Early online date||25 Jan 2022|
|Publication status||Published - 1 Jan 2023|
Bibliographical noteFunding Information:
This work was supported in part by the National Natural Science Foundation of China under Grants 62032011, 62172218, and 61672273
© 1979-2012 IEEE.
- multi-scale and -feature modules
- noisy point clouds
- normal estimation
- point cloud denoising