TACO: a Benchmark for Connectivity-invariance in Shape Correspondence

In real-world scenarios, a major limitation for shape-matching datasets is represented by having all the meshes of the same subject share their connectivity across different poses. Specifically, similar connectivities could provide a significant bias for shape matching algorithms, simplifying the matching process and potentially leading to correspondences based on the recurring triangle patterns rather than geometric correspondences between mesh parts. As a consequence, the resulting correspondence may be meaningless, and the evaluation of the algorithm may be misled. To overcome this limitation, we introduce TACO, a new dataset where meshes representing the same subject in different poses do not share the same connectivity, and we compute new ground truth correspondences between shapes. We extensively evaluate our dataset to ensure that ground truth isometries are properly preserved. We also use our dataset for validating state-of-the-art shape-matching algorithms, verifying a degradation in performance when the connectivity gets altered.