Learning quadrangulated patches for 3D shape parameterization and completion

Kripasindhu Sarkar, Kiran Varanasi, Didier Stricker

In: International Conference on 3D Vision 2017. International Conference on 3DVision (3DV-2017) 5th October 10-12 Qingdao China IEEE 2017.


We propose a novel 3D shape parameterization by surface patches, that are oriented by 3D mesh quadrangulation of the shape. By encoding 3D surface detail on local patches, we learn a patch dictionary that identifies principal surface features of the shape. Unlike previous methods, we are able to encode surface patches of variable size as determined by the user. We propose novel methods for dictionary learning and patch reconstruction based on the query of a noisy input patch with holes. We evaluate the patch dictionary towards various applications in 3D shape inpainting, denoising and compression. Our method is able to predict missing vertices and inpaint moderately sized holes. We demonstrate a complete pipeline for reconstructing the 3D mesh from the patch encoding. We validate our shape parameterization and reconstruction methods on both synthetic shapes and real world scans. We show that our patch dictionary performs successful shape completion of complicated surface textures.


PID5041137.pdf (pdf, 5 MB)

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz