A5114406722- 3D Shape Modeling and Analysis
- Advanced Numerical Analysis Techniques
- Optical measurement and interference techniques
- Computer Graphics and Visualization Techniques
- Manufacturing Process and Optimization
- Industrial Technology and Control Systems
China University of Geosciences
2023
Point cloud denoising is a fundamental and challenging problem in geometry processing. Existing methods typically involve direct of noisy input or filtering raw normals followed by point position updates. Recognizing the crucial relationship between normal filtering, we re-examine this from multitask perspective propose an end-to-end network called PCDNF for joint filtering-based denoising. We introduce auxiliary task to enhance network's ability remove noise while preserving geometric...
Recovering high quality surfaces from noisy point clouds, known as cloud denoising, is a fundamental yet challenging problem in geometry processing. Most of the existing methods either directly denoise input or filter raw normals followed by updating positions. Motivated essential interplay between denoising and normal filtering, we revisit multitask perspective, propose an end-to-end network, named PCDNF, to clouds via joint filtering. In particular, introduce auxiliary filtering task help...