Learning Quadrangulated Patches For 3D Shape Processing
This addresses surface repair for 3D shapes, such as in computer graphics or scanning, but is incremental as it builds on existing 2D inpainting techniques.
The paper tackles the problem of surface completion and inpainting for 3D shapes by learning generative models on local patches parameterized via quadrangulation, achieving better results than previous geometry-based methods.
We propose a system for surface completion and inpainting of 3D shapes using generative models, learnt on local patches. Our method uses a novel encoding of height map based local patches parameterized using 3D mesh quadrangulation of the low resolution input shape. This provides us sufficient amount of local 3D patches to learn a generative model for the task of repairing moderate sized holes. Following the ideas from the recent progress in 2D inpainting, we investigated both linear dictionary based model and convolutional denoising autoencoders based model for the task for inpainting, and show our results to be better than the previous geometry based method of surface inpainting. We validate our method on both synthetic shapes and real world scans.