mlsanityData to 7 Oct 2026

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

arXiv 1911.10949 ↗First posted 25 Nov 2019cs.CV cs.GR cs.LGcited by 118

Not on the map. Why?

Abstract (arXiv)

We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.

Key facts. Cited by 118 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 20; 2023: 28; 2024: 30; 2025: 16; 2026: 4.

118 papers.

Sort:

By area:

  1. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  2. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  3. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  4. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  5. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  6. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generationcited by 133
  7. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  8. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  9. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
  10. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 77
  11. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  12. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 66
38 more
  1. 2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
  2. 2021StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objectscited by 57
  3. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
  4. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  5. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 41
  6. 2024MeshArt: Generating Articulated Meshes with Structure-Guided Transformerscited by 40
  7. 2021SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Datacited by 38
  8. 2022Breaking Bad: A Dataset for Geometric Fracture and Reassemblycited by 38
  9. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 36
  10. 2023PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervisioncited by 36
  11. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 35
  12. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  13. 2022Learning to Generate 3D Shapes from a Single Examplecited by 31
  14. 2024TransCAD: A Hierarchical Transformer for CAD Sequence Inference from Point Cloudscited by 29
  15. 2023HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3Dcited by 27
  16. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 26
  17. 2024OpenECAD: An Efficient Visual Language Model for Editable 3D-CAD Designcited by 26
  18. 20233DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Processcited by 25
  19. 2023NAP: Neural 3D Articulation Priorcited by 25
  20. 2023Category-Level Multi-Part Multi-Joint 3D Shape Assemblycited by 22
  21. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  22. 2022Point Scene Understanding via Disentangled Instance Mesh Reconstructioncited by 20
  23. 2023Graph Transformer GANs for Graph-Constrained House Generationcited by 19
  24. 2023Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterpartscited by 18
  25. 20223D Part Assembly Generation with Instance Encoded Transformercited by 17
  26. 2024Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passingcited by 17
  27. 2024Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solvingcited by 17
  28. 2022ANISE: Assembly-based Neural Implicit Surface rEconstructioncited by 16
  29. 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Cloudscited by 15
  30. 2024PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verifycited by 14
  31. 2024PASTA: Controllable Part-Aware Shape Generation with Autoregressive Transformerscited by 14
  32. 2021AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assembliescited by 13
  33. 2022Implicit field supervision for robust non-rigid shape matchingcited by 13
  34. 2023Scalable Geometric Fracture Assembly via Co-creation Space among Assemblerscited by 13
  35. 2024Topology-Aware Latent Diffusion for 3D Shape Generationcited by 13
  36. 2022An Implicit Parametric Morphable Dental Modelcited by 12
  37. 2024GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesiscited by 12
  38. 2025GARF: Learning Generalizable 3D Reassembly for Real-World Fracturescited by 12

50 most cited of 118 All 118 (JSON)