A. Dubrovina, F. Xia, P. Achlioptas, M. Shalah, R. Groscot, and L. Guibas, Composite Shape Modeling via Latent Space Factorization, IEEE International Conference on Computer Vision (ICCV), 2019.


We present a novel neural network architecture, termed Decomposer-Composer, for semantic structure-aware 3D shape modeling. Our method utilizes an auto-encoder-based pipeline, and produces a novel factorized shape latent space, where the semantic structure of the shape collection translates into a data-dependent subspace factorization, and where shape composition and decomposition become simple linear operations on the embedding coordinates. We further propose to model shape assembly using an explicit learned part deformation module, which utilizes a 3D spatial transformer network to perform an in network volumetric grid deformation, and which allows us to train the whole system end-to-end. The resulting network allows us to perform part-level shape manipulation, unattainable by existing approaches. Our extensive ablation study, comparison to baseline methods and qualitative analysis demonstrate the improved performance of the proposed method.


author = {Dubrovina, Anastasia and Xia, Fei and Achlioptas,  Panos and Shalah, Mira and Grvoscot, Raphael and Guibas, Leonidas},
year = {2019},
title = {Composite Shape Modeling via Latent Space Factorization},
journal = {International Conference Computer Vision},