P2S

홈페이지 · 논문 4편

We introduced this dataset in Points2Surf, a method that turns point clouds into meshes. It consists of objects from the _ABC Dataset_, a collection of _Famous_ meshes and objects from _Thingi10k_. These are mostly single objects per file, sometimes a couple of disconnected objects. Objects from the _ABC Dataset_ are CAD-models, the others are mostly statues with organic structures. We created realistic point clouds using a simulated time-of-flight sensor from _BlenSor_. The point clouds have typical artifacts like noise and scan shadows. Finally, we created training data consisting of randomly sampled query points with their ground-truth signed distance. The query points are 50% uniformly distributed in the unit cube and 50% near the surface with some random offset. The training set consists of 4950 _ABC_ objects with varying number of scans and noise strength. The validation sets are the same as the test set. The _ABC_ test sets contain 100 objects, _Famous_ 22 and _Thingi10k_ 100. The test set variants are as follows: (1) _ABC_ var (like training set), no noise, strong noise; (2) _Famous_ no noise, medium noise, strong noise, sparse, dense scans; (3) _Thingi10k_ no noise, medium noise, strong noise, sparse, dense scans