3D synthesis of man-made objects based on fine-grained parts. (August 2018)

• Record Type: Journal Article
• Authors: Gonzalez, Diego; van Kaick, Oliver
• Is Part Of: Computers & graphics. Volume 74(2018)
• Page Start: 150
• Page End: 160
• Publication Date: 2018-08
• Subjects: Shape synthesis -- Shape segmentation -- Shape analysis; Computer graphics -- Periodicals; 006.6
• DOI: 10.1016/j.cag.2018.05.016
• Languages: English
• ISSNs: 0097-8493

Abstract

Highlights: We present a complete pipeline for 3D synthesis of man-made shapes based on recombining fine-grained segments extracted from an input set of shapes. By using fine-grained segments, our method can synthesize shapes that have a wide range of local fine details. We show that we can generate a plausible shape, by preserving the structure and topology of an input template, and by maximizing an energy function. Unlike most previous approaches, our method does not require a semantic segmentation, nor part correspondences between the shapes of the input dataset. Graphical abstract: Abstract: We present a novel approach for 3D shape synthesis from a collection of existing models. The main idea of our approach is to synthesize shapes by recombining fine-grained parts extracted from the existing models based purely on the objects' geometry. Thus, unlike most previous works, a key advantage of our method is that it does not require a semantic segmentation, nor part correspondences between the shapes of the input set. Our method uses a template shape to guide the synthesis. After extracting a set of fine-grained segments from the input dataset, we compute the similarity among the segments in the collection and segments of the template using shape descriptors. Next, we use the similarity estimates to select, from the set of fine-grained segments, compatible replacements for each part of the template. By sampling different segments for each part of the template, and by using different templates, our method can synthesize many distinct shapes that have a variety of local fine details. Additionally, we maintain the plausibility of the objects by preserving the general structure of the template. We show with several experiments performed on different datasets that our algorithm can be used for synthesizing a wide variety of man-made objects.