# Learning Body-Aware 3D Shape Generative Models

arXiv: https://arxiv.org/abs/2112.07022 · HTML: https://mlsanity.com/paper/2112.07022/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [Resolving 3D Human Pose Ambiguities with 3D Scene Constraints](https://mlsanity.com/paper/1908.06963/) (2019)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [Populating 3D Scenes by Learning Human-Scene Interaction](https://mlsanity.com/paper/2012.11581/) (2020)
- [Capturing Hands in Action using Discriminative Salient Points and Physics Simulation](https://mlsanity.com/paper/1506.02178/) (2015)
- [SDM-NET: Deep Generative Network for Structured Deformable Mesh](https://mlsanity.com/paper/1908.04520/) (2019)
- [Deep Implicit Moving Least-Squares Functions for 3D Reconstruction](https://mlsanity.com/paper/2103.12266/) (2021)
- [StructureNet: Hierarchical Graph Networks for 3D Shape Generation](https://mlsanity.com/paper/1908.00575/) (2019)
- [Fast Tetrahedral Meshing in the Wild](https://mlsanity.com/paper/1908.03581/) (2019)
- [3D ShapeNets: A Deep Representation for Volumetric Shapes](https://mlsanity.com/paper/1406.5670/) (2014)
- [Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapes](https://mlsanity.com/paper/1809.07917/) (2018)
- [GRASS: Generative Recursive Autoencoders for Shape Structures](https://mlsanity.com/paper/1705.02090/) (2017)
- [SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2108.04476/) (2021)
- [ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis](https://mlsanity.com/paper/2009.08026/) (2020)

## Built on by (most cited first, 5 of 5)

- [Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation](https://mlsanity.com/paper/2302.00190/) (2023)
- [Scene Synthesis from Human Motion](https://mlsanity.com/paper/2301.01424/) (2023)
- [Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication](https://mlsanity.com/paper/2405.18515/) (2024)
- [CRAFT: Designing Creative and Functional 3D Objects](https://mlsanity.com/paper/2412.03889/) (2024)
- [Efficient Human-Contact Representation for Human-Scene Interaction](https://mlsanity.com/paper/2608.09388/) (2026)

## Abstract (arXiv)

The shape of many objects in the built environment is dictated by their relationships to the human body: how will a person interact with this object? Existing data-driven generative models of 3D shapes produce plausible objects but do not reason about the relationship of those objects to the human body. In this paper, we learn body-aware generative models of 3D shapes. Specifically, we train generative models of chairs, an ubiquitous shape category, which can be conditioned on a given body shape or sitting pose. The body-shape-conditioned models produce chairs which will be comfortable for a person with the given body shape; the pose-conditioned models produce chairs which accommodate the given sitting pose. To train these models, we define a "sitting pose matching" metric and a novel "sitting comfort" metric. Calculating these metrics requires an expensive optimization to sit the body into the chair, which is too slow to be used as a loss function for training a generative model. Thus, we train neural networks to efficiently approximate these metrics. We use our approach to train three body-aware generative shape models: a structured part-based generator, a point cloud generator, and an implicit surface generator. In all cases, our approach produces models which adapt their output chair shapes to input human body specifications.