# StructEdit: Learning Structural Shape Variations

arXiv: https://arxiv.org/abs/1911.11098 · HTML: https://mlsanity.com/paper/1911.11098/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 23 of 23)

- [SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry](https://mlsanity.com/paper/2302.10237/) (2023)
- [PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision](https://mlsanity.com/paper/2303.09554/) (2023)
- [PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning](https://mlsanity.com/paper/2112.05136/) (2021)
- [OctField: Hierarchical Implicit Functions for 3D Modeling](https://mlsanity.com/paper/2111.01067/) (2021)
- [3D Part Assembly Generation with Instance Encoded Transformer](https://mlsanity.com/paper/2207.01779/) (2022)
- [NeuForm: Adaptive Overfitting for Neural Shape Editing](https://mlsanity.com/paper/2207.08890/) (2022)
- [PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformers](https://mlsanity.com/paper/2407.13677/) (2024)
- [AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies](https://mlsanity.com/paper/2105.12238/) (2021)
- [Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects](https://mlsanity.com/paper/2110.04411/) (2021)
- [LADIS: Language Disentanglement for 3D Shape Editing](https://mlsanity.com/paper/2212.05011/) (2022)
- [LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies](https://mlsanity.com/paper/2108.13459/) (2021)
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://mlsanity.com/paper/2204.08824/) (2022)
- [ParSEL: Parameterized Shape Editing with Language](https://mlsanity.com/paper/2405.20319/) (2024)
- [RPG: Learning Recursive Point Cloud Generation](https://mlsanity.com/paper/2105.14322/) (2021)
- [Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection](https://mlsanity.com/paper/2312.11867/) (2023)
- [GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling](https://mlsanity.com/paper/2504.01483/) (2025)
- [Attention-based Part Assembly for 3D Volumetric Shape Modeling](https://mlsanity.com/paper/2304.10986/) (2023)
- [Autoregressive Generation of Static and Growing Trees](https://mlsanity.com/paper/2502.04762/) (2025)
- [Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing](https://mlsanity.com/paper/2211.00382/) (2022)
- [StructRe: Rewriting for Structured Shape Modeling](https://mlsanity.com/paper/2311.17510/) (2023)
- [3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation](https://mlsanity.com/paper/2211.09770/) (2022)
- [DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives](https://mlsanity.com/paper/2603.16133/) (2026)
- [SCULPT: Subtractive Composition for 3D Part Generation](https://mlsanity.com/paper/2608.13541/) (2026)

## Abstract (arXiv)

Learning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape, transferring edits from one shape to another, and many other applications in 3D content creation. The common approach of encoding shapes as points in a high-dimensional latent feature space suggests treating shape differences as vectors in that space. Instead, we treat shape differences as primary objects in their own right and propose to encode them in their own latent space. In a setting where the shapes themselves are encoded in terms of fine-grained part hierarchies, we demonstrate that a separate encoding of shape deltas or differences provides a principled way to deal with inhomogeneities in the shape space due to different combinatorial part structures, while also allowing for compactness in the representation, as well as edit abstraction and transfer. Our approach is based on a conditional variational autoencoder for encoding and decoding shape deltas, conditioned on a source shape. We demonstrate the effectiveness and robustness of our approach in multiple shape modification and generation tasks, and provide comparison and ablation studies on the PartNet dataset, one of the largest publicly available 3D datasets.