From Noisy Point Clouds to Complete Ear Shapes: Unsupervised Pipeline

Ears are a particularly difficult region of the human face to model, not only due to the non-rigid deformations existing between shapes but also to the challenges in processing the retrieved data. The first step towards obtaining a good model is to have complete scans in correspondence, but these usually present a higher amount of occlusions, noise and outliers when compared to most face regions, thus requiring a specific procedure. Therefore, we propose a complete pipeline taking as input unordered 3D point clouds with the aforementioned problems, and producing as output a dataset in correspondence, with completion of the missing data. We provide a comparison of several state-of-the-art registration and shape completion methods, concluding on the best choice for each of the steps.

Automated summary

Ears are a challenging region to model on the human face due to non-rigid deformations and difficulties in processing the data. The proposed pipeline aims to handle unordered 3D point clouds with issues such as occlusions and outliers, ultimately producing a dataset with completed missing data. Comparisons of registration and shape completion methods are provided to determine the best choices for each step.