Affiliation:
1. Faculty of Electrical Engineering and Computing, University of Zagreb, Unska 3, 10000 Zagreb, Croatia
Abstract
Recently, there has been renewed interest in signed distance bound representations due to their unique properties for 3D shape modelling. This is especially the case for deep learning-based bounds. However, it is beneficial to work with polygons in most computer graphics applications. Thus, in this paper, we introduce and investigate an asymptotically fast method for transforming signed distance bounds into polygon meshes. This is achieved by combining the principles of sphere tracing (or ray marching) with traditional polygonization techniques, such as marching cubes. We provide theoretical and experimental evidence that this approach is of the O(N2logN) computational complexity for a polygonization grid with N3 cells. The algorithm is tested on both a set of primitive shapes and signed distance bounds generated from point clouds by machine learning (and represented as neural networks). Given its speed, implementation simplicity, and portability, we argue that it could prove useful during the modelling stage as well as in shape compression for storage.
Funder
Croatian National Recovery and Resilience Plan
European Defence Fund
Reference28 articles.
1. Sphere Tracing: A Geometric Method for the Antialiased Ray Tracing of Implicit Surfaces;Hart;Vis. Comput.,1994
2. Hart, J.C., Sandin, D.J., and Kauffman, L.H. (1989). ACM SIGGRAPH Computer Graphics, Association for Computing Machinery.
3. Davies, T., Nowrouzezahrai, D., and Jacobson, A. (2020). Overfit Neural Networks as a Compact Shape Representation. arXiv.
4. Chen, Z., and Zhang, H. (2019, January 15–20). Learning Implicit Fields for Generative Shape Modeling. Proceedings of the CVPR, Long Beach, CA, USA.
5. Park, J.J., Florence, P., Straub, J., Newcombe, R., and Lovegrove, S. (2019, January 15–20). DeepSDF: Learning Continuous Signed Distance Functionsfor Shape Representation. Proceedings of the CVPR, Long Beach, CA, USA.