mlsanityData to 7 Oct 2026

PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimization

arXiv 2502.12985 ↗First posted 18 Feb 2025cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Accurate 3D shape representation is essential in engineering applications such as design, optimization, and simulation. In practice, engineering workflows require structured, part-based representations, as objects are inherently designed as assemblies of distinct components. However, most existing methods either model shapes holistically or decompose them without predefined part structures, limiting their applicability in real-world design tasks. We propose PartSDF, a supervised implicit representation framework that explicitly models composite shapes with independent, controllable parts while maintaining shape consistency. Thanks to its simple but innovative architecture, PartSDF outperforms both supervised and unsupervised baselines in reconstruction and generation tasks. We further demonstrate its effectiveness as a structured shape prior for engineering applications, enabling precise control over individual components while preserving overall coherence. Code available at https://github.com/cvlab-epfl/PartSDF.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 69 of its 93 references that are in the map. First posted on arXiv 18 Feb 2025.

Builds on

69 of 93 references.

References · 69

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  10. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
38 more
  1. 2020Convolutional Occupancy Networkscited by 760
  2. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  3. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  4. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  5. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  6. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  7. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 541
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  10. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  11. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  12. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  13. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  14. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  15. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  16. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  17. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  18. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  19. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  20. 2021Shape As Points: A Differentiable Poisson Solvercited by 186
  21. 2022From data to functa: Your data point is a function and you can treat it like onecited by 183
  22. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  23. 2019CvxNet: Learnable Convex Decompositioncited by 173
  24. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  25. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 118
  26. 2019SDM-NET: Deep Generative Network for Structured Deformable Meshcited by 113
  27. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 113
  28. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  29. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  30. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  31. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  32. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  33. 2019BAE-NET: Branched Autoencoder for Shape Co-Segmentationcited by 89
  34. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  35. 20173D-PRNN: Generating Shape Primitives with Recurrent Neural Networkscited by 77
  36. 2022AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutionscited by 77
  37. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 75
  38. 2024DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarkscited by 74

50 most cited of 69 All 69 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 3.

8 papers.

  1. 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
  2. 2025Neural Implicit Heart Coordinates: 3D cardiac shape reconstruction from sparse segmentationscited by 4
  3. 2025Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Modelscited by 1
  4. 2026Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidancecited by 1
  5. 2026VecHeart: Holistic Four-Chamber Cardiac Anatomy Modeling via Hybrid VecSetscited by 1
  6. 2026S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fieldscited by 1
  7. 2025Hierarchical Transformers for Unsupervised 3D Shape Abstractioncited by 0
  8. 2025GLUE: Coordinating Pre-Trained Generative Models for System-Level Designcited by 0