Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation

arXiv:2403.01619v1 Announce Type: new
Abstract: Existing 3D mesh shape evaluation metrics mainly focus on the overall shape but are usually less sensitive to local details. This makes them inconsistent with human evaluation, as human perception cares about both overall and detailed shape. In this paper, we propose an analytic metric named Spectrum Area Under the Curve Difference (SAUCD) that demonstrates better consistency with human evaluation. To compare the difference between two shapes, we first transform the 3D mesh to the …

abstract arxiv auc cs.cv cs.gr difference evaluation evaluation metrics focus human mesh metrics paper perception spectrum them type