Surface modeling using multi-view range and color images

This paper presents a framework of surface modeling from multi-view range and color images. The input to the algorithms are pairs of triangle meshes and color images, and each pair is obtained by a single-view scanning. In the proposed framework, the triangle meshes from raw data are first processed by the novel surface denoising algorithm based on area decreasing flow, which avoids the difficulty in curvature estimation of mean curvature flow. The proposed adaptive triangle mesh smoothing algorithm is based on crease edge strength of each vertex and uses tensor voting of the normal vector field inside a geodesic window. Surfaces from multiple views are then integrated into a single 3D model. Two integration approaches are discussed, which are based on mesh zippering and implicit surface fusion, respectively. Color images are incorporated to generate textured models. The reconstructed surfaces are finally post-processed by volumetric smoothing and filling the holes. Experimentation using two different range scanners shows that the proposed surface modeling framework is robust and flexible in processing data from different types of range scanners.