Towards Detailed 3D Modeling: Mesh Super-Resolution via Deformation

This paper presents a method for constructing a detailed mesh model by deforming a coarse mesh model using surface normals estimated from images. Mesh representation is a 3D data structure that can represent a detailed shape with fewer parameters compared with other data structures. Multi-view stereo (MVS) algorithms are suitable for reconstructing a detailed mesh model from images captured from different viewpoints; however, the computation time increases rapidly as the resolution and the number of images increase. To overcome this problem, we propose a novel approach to deform a coarse mesh model. We first reconstruct a coarse mesh model by applying the Delaunay triangulation to a coarse point cloud obtained through structure-from-motion. The resulting model is deformed based on the changes in the surface normals estimated from images. In our experiments, we demonstrate that our method constructs detailed 3D models faster than the MVS with a single model dataset and general scene dataset. Contribution-Mesh deformation based on the normal maps generates a detailed mesh model.