# LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies

arXiv: https://arxiv.org/abs/2108.13459 · HTML: https://mlsanity.com/paper/2108.13459/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 21 of 21)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [PolyGen: An Autoregressive Generative Model of 3D Meshes](https://mlsanity.com/paper/2002.10880/) (2020)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs](https://mlsanity.com/paper/1703.09438/) (2017)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [Learning to Infer and Execute 3D Shape Programs](https://mlsanity.com/paper/1901.02875/) (2019)
- [Fast, Diverse and Accurate Image Captioning Guided By Part-of-Speech](https://mlsanity.com/paper/1805.12589/) (2018)
- [Z-Forcing: Training Stochastic Recurrent Networks](https://mlsanity.com/paper/1711.05411/) (2017)
- [Composite Shape Modeling via Latent Space Factorization](https://mlsanity.com/paper/1901.02968/) (2019)
- [Learning Generative Models of Shape Handles](https://mlsanity.com/paper/2004.03028/) (2020)
- [StructEdit: Learning Structural Shape Variations](https://mlsanity.com/paper/1911.11098/) (2019)
- [Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning](https://mlsanity.com/paper/1908.08529/) (2019)

## Built on by (most cited first, 8 of 8)

- [NeuralTailor: Reconstructing Sewing Pattern Structures from 3D Point Clouds of Garments](https://mlsanity.com/paper/2201.13063/) (2022)
- [Convex Decomposition of Indoor Scenes](https://mlsanity.com/paper/2307.04246/) (2023)
- [3D Generative Model Latent Disentanglement via Local Eigenprojection](https://mlsanity.com/paper/2302.12798/) (2023)
- [StructRe: Rewriting for Structured Shape Modeling](https://mlsanity.com/paper/2311.17510/) (2023)
- [Improved Convex Decomposition with Ensembling and Negative Primitives](https://mlsanity.com/paper/2405.19569/) (2024)
- [Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervision](https://mlsanity.com/paper/2511.16650/) (2025)
- [3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation](https://mlsanity.com/paper/2211.09770/) (2022)
- [Diverse Part Synthesis for 3D Shape Creation](https://mlsanity.com/paper/2401.09384/) (2024)

## Abstract (arXiv)

Generative models for 3D shapes represented by hierarchies of parts can generate realistic and diverse sets of outputs. However, existing models suffer from the key practical limitation of modelling shapes holistically and thus cannot perform conditional sampling, i.e. they are not able to generate variants on individual parts of generated shapes without modifying the rest of the shape. This is limiting for applications such as 3D CAD design that involve adjusting created shapes at multiple levels of detail. To address this, we introduce LSD-StructureNet, an augmentation to the StructureNet architecture that enables re-generation of parts situated at arbitrary positions in the hierarchies of its outputs. We achieve this by learning individual, probabilistic conditional decoders for each hierarchy depth. We evaluate LSD-StructureNet on the PartNet dataset, the largest dataset of 3D shapes represented by hierarchies of parts. Our results show that contrarily to existing methods, LSD-StructureNet can perform conditional sampling without impacting inference speed or the realism and diversity of its outputs.