We analyze unorganized model collections using template-based abstractions to create a low-dimensional parameterized embedding of the underlying shape space. The user then explores the parameterized space to create novel models by probing the empty regions (e.g., in red rectangles). In each case, a model was synthesized by significantly deforming and combining parts from the input models.
ShapeSynth: Parameterizing Model Collections for Coupled Shape Exploration and Synthesis
Melinos Averkiou, Vladimir Kim, Youyi Zheng, Niloy J. Mitra
Eurographics 2014


Recent advances in modeling tools enable non-expert users to synthesize novel shapes by assembling parts extracted from model databases. A major challenge for these tools is to provide users with relevant parts, which is especially difficult for large repositories with significant geometric variations. In this paper we analyze unorganized collections of 3D models to facilitate explorative shape synthesis by providing high-level feedback of possible synthesizable shapes. By jointly analyzing arrangements and shapes of parts across models, we hierarchically embed the models into low-dimensional spaces. The user can then use the parameterization to explore the existing models by clicking in different areas or by selecting groups to zoom on specific shape clusters. More importantly, any point in the embedded space can be lifted to an arrangement of parts to provide an abstracted view of possible shape variations. The abstraction can further be realized by appropriately deforming parts from neighboring models to produce synthesized geometry. Our experiments show that users can rapidly generate plausible and diverse shapes using our system, which also performs favorably with respect to previous modeling tools.


Code, data:

Please download supplementary material from the following links: source (10MB), data (300MB), big_data (4GB).


We are grateful to Evangelos Kalogerakis and the reviewers for their comments; Siddhartha Chaudhuri for helping with the comparison. We thank Bongjin Koo and Yanir Kleiman for their comments, and James Hennessey for the video voiceover. This project was supported in part by a Marie Curie CIG and ERC Starting Grant SmartGeometry.


AUTHOR = "Melinos Averkiou and Vladimir Kim and Youyi Zheng and Niloy J. Mitra",
TITLE = "ShapeSynth: Parameterizing Model Collections
for Coupled Shape Exploration and Synthesis",
JOURNAL = "Computer Graphics Forum (Special issue of Eurographics 2014)",
YEAR = "2014", 
numpages = {10},

paper (7MB)
back to publications
back to homepage