mlsanityData to 14 Oct 2026

Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection

arXiv 2312.11867 ↗First posted 19 Dec 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Ideal part editing should guarantee the diversity of edited parts, the fidelity to the remaining parts, and the quality of the results. However, previous methods do not disentangle each part completely, which means the edited parts will affect the others, resulting in poor diversity and fidelity. In addition, some methods lack constraints between parts, which need manual selections of edited results to ensure quality. Therefore, we propose a four-stage process for point cloud part editing: Segmentation, Generation, Assembly, and Selection. Based on this process, we introduce SGAS, a model for part editing that employs two strategies: feature disentanglement and constraint. By independently fitting part-level feature distributions, we realize the feature disentanglement. By explicitly modeling the transformation from object-level distribution to part-level distributions, we realize the feature constraint. Considerable experiments on different datasets demonstrate the efficiency and effectiveness of SGAS on point cloud part editing. In addition, SGAS can be pruned to realize unsupervised part-aware point cloud generation and achieves state-of-the-art results.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 29 of its 46 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

29 of 46 references.

References · 29

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2017Improved Training of Wasserstein GANscited by 2,235
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  6. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  7. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  8. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  9. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  10. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  11. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  12. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
17 more
  1. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  2. 2020Deep Learning for Procedural Content Generationcited by 73
  3. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  4. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  5. 2022Autoregressive 3D Shape Generation via Canonical Mappingcited by 37
  6. 2019Learning Part Generation and Assembly for Structure-aware Shape Synthesiscited by 36
  7. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  8. 2019Composite Shape Modeling via Latent Space Factorizationcited by 31
  9. 2020COALESCE: Component Assembly by Learning to Synthesize Connectionscited by 30
  10. 2019StructEdit: Learning Structural Shape Variationscited by 23
  11. 2021Learning to Generate 3D Shapes with Generative Cellular Automatacited by 22
  12. 2021Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstructioncited by 16
  13. 2021Attention-based Transformation from Latent Features to Point Cloudscited by 8
  14. 2021The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Partscited by 7
  15. 2020LPMNet: Latent Part Modification and Generation for 3D Point Cloudscited by 3
  16. 2023Attention-based Part Assembly for 3D Volumetric Shape Modelingcited by 3
  17. 2022Probabilistic Shape Completion by Estimating Canonical Factors with Hierarchical VAEcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024View-Consistent 3D Editing with Gaussian Splattingcited by 67
  2. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesiscited by 34
  3. 2025SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generationcited by 4
  4. 2025Aligning Instance-Semantic Sparse Representation towards Unsupervised Object Segmentation and Shape Abstraction with Repeatable Primitivescited by 2