# Composite Shape Modeling via Latent Space Factorization

## TL;DR

This paper introduces Decomposer-Composer, a neural network that creates a factorized shape embedding space for semantic 3D shape modeling, enabling part-level manipulation through end-to-end training.

## Contribution

The paper proposes a novel auto-encoder architecture with a data-dependent factorized embedding space and a learned part deformation module for semantic 3D shape modeling.

## Key findings

- Improved shape manipulation capabilities.
- Effective part decomposition and recomposition.
- End-to-end trainable deformation module.

## Abstract

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 embedding space, where the semantic structure of the shape collection translates into a data-dependent sub-space 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.