DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentation

arXiv:2311.13125v2 Announce Type: replace
Abstract: We present an unsupervised 3D shape co-segmentation method which learns a set of deformable part templates from a shape collection. To accommodate structural variations in the collection, our network composes each shape by a selected subset of template parts which are affine-transformed. To maximize the expressive power of the part templates, we introduce a per-part deformation network to enable the modeling of diverse parts with substantial geometry variations, while imposing constraints on the deformation capacity …

arxiv auto cs.cv cs.gr encoder fine-grained segmentation type