Learning Shape Templates with Structured Implicit Functions
This addresses the need for automated shape templates in graphics and vision, replacing hand-made libraries, but is incremental as it adapts an existing representation to machine learning.
The paper tackles the problem of learning a general 3D shape template from data to handle varied geometry and topology, using structured implicit functions, and shows it enables applications like shape exploration and semantic segmentation.
Template 3D shapes are useful for many tasks in graphics and vision, including fitting observation data, analyzing shape collections, and transferring shape attributes. Because of the variety of geometry and topology of real-world shapes, previous methods generally use a library of hand-made templates. In this paper, we investigate learning a general shape template from data. To allow for widely varying geometry and topology, we choose an implicit surface representation based on composition of local shape elements. While long known to computer graphics, this representation has not yet been explored in the context of machine learning for vision. We show that structured implicit functions are suitable for learning and allow a network to smoothly and simultaneously fit multiple classes of shapes. The learned shape template supports applications such as shape exploration, correspondence, abstraction, interpolation, and semantic segmentation from an RGB image.