Contour-aware 3D reconstruction of side-view sketches. (December 2018)

• Record Type: Journal Article
• Authors: Ramos, Saulo; Trevisan, Diogo Fernando; C. Batagelo, Harlen; Costa Sousa, Mario; Gois, João Paulo
• Is Part Of: Computers & graphics. Volume 77(2018)
• Page Start: 97
• Page End: 107
• Publication Date: 2018-12
• Subjects: Sketch-based modeling -- Direct 3D reconstruction -- HRBF implicits -- Hermitian data; Computer graphics -- Periodicals; 006.6
• DOI: 10.1016/j.cag.2018.09.009
• Languages: English
• ISSNs: 0097-8493

Abstract

Highlights: A new strategy of 3D reconstruction by contour constraints in drawings based on Hermitian Radial Basis Functions (HRBF). The use of a normal-driven estimate of depth in shapes to produce 3D Hermitian Data. The capability of reconstructing parts with flexibility based on the adjustment of points and their normals according to the desired model. An improvement on part classification of the sketches. A skeleton-free and interpolatory approach for 3D reconstruction from side-view sketches. Graphical abstract: Abstract: The 3D reconstruction from a single 2D side-view sketch faces challenges in capturing details of the curves and inferring the hidden parts. Here, we introduce an approach that ensures the 2D contours are interpolated to a suitable 3D reconstruction while capturing the small details of the sketch. To this end, we propose a novel strategy that combines a proper 3D Hermitian data generation from the vicinity of the sketches with an approach for identification and completion of sketch curves. Feasible 3D models are then generated using Hermitian Radial Basis Functions (HRBF) Implicit Surfaces. Results indicate that our approach provides not only more detailed 3D reconstructed models but also more perceptual agreement from the input sketches in comparison to previous work.