Category-Agnostic Neural Object Rigging

Encoder Quadruped Decoder Blobs Edited Blobs Edited Result Encoder Decoder Fish Blobs Edited Blobs Edited Result Edit Blobs Edit Blobs Encoder Decoder Glasses Blobs Edited Blobs Edited Result Edit Blobs Figure 1. We introduce Category-Agnostic Neural Object Rigging (CANOR), a novel approach that learns to discover a low-dimensional pose space for dynamic objects. The representation is learned from animated 3D sequences of a deformable object category in an unsupervised fashion without relying on any category-specific expert knowledge. By decomposing each object's geometry into a sparse set of feature-embedded blobs, CANOR enables intuitive manipulation of object poses by editing the blobs. This representation captures interpretable motion structures for a diverse range of dynamic object categories.