mlsanityData to 7 Oct 2026

SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation

arXiv 2303.12236 ↗First posted 21 Mar 2023cs.CVcited by 66

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

We present a cascaded diffusion model based on a part-level implicit 3D representation. Our model achieves state-of-the-art generation quality and also enables part-level shape editing and manipulation without any additional training in conditional setup. Diffusion models have demonstrated impressive capabilities in data generation as well as zero-shot completion and editing via a guided reverse process. Recent research on 3D diffusion models has focused on improving their generation capabilities with various data representations, while the absence of structural information has limited their capability in completion and editing tasks. We thus propose our novel diffusion model using a part-level implicit representation. To effectively learn diffusion with high-dimensional embedding vectors of parts, we propose a cascaded framework, learning diffusion first on a low-dimensional subspace encoding extrinsic parameters of parts and then on the other high-dimensional subspace encoding intrinsic attributes. In the experiments, we demonstrate the outperformance of our method compared with the previous ones both in generation and part-level completion and manipulation tasks.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 59 of its 72 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

59 of 72 references.

Closest ancestors · 7

Same direction, newest first

  1. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  2. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models1 Dec
  3. 20223D Neural Field Generation using Triplane Diffusion30 Nov
  4. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions24 Nov
  5. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan
  7. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 52

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  7. 2022Classifier-Free Diffusion Guidancecited by 5,717
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  9. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  11. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  12. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
38 more
  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  2. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  4. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  7. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  8. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  9. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  10. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  11. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  12. 2020PolyGen: An Autoregressive Generative Model of 3D Meshescited by 267
  13. 2016Revisiting Classifier Two-Sample Testscited by 258
  14. 2020Learning Gradient Fields for Shape Generationcited by 245
  15. 2019Learning Shape Templates with Structured Implicit Functionscited by 242
  16. 2022Riemannian Score-Based Generative Modellingcited by 216
  17. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  18. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  19. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  20. 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
  21. 2019CvxNet: Learnable Convex Decompositioncited by 173
  22. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  23. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  24. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  25. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  26. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  27. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  28. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 101
  29. 20223DILG: Irregular Latent Grids for 3D Generative Modelingcited by 92
  30. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  31. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  32. 2022ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Modelcited by 62
  33. 2019ShapeGlot: Learning Language for Shape Differentiationcited by 54
  34. 20213D Shape Generation with Grid-based Implicit Functionscited by 48
  35. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  36. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  37. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  38. 2021PartGlot: Learning Shape Part Segmentation from Language Reference Gamescited by 30

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 9; 2024: 21; 2025: 22; 2026: 14.

66 papers.

Sort:

By area:

  1. 2025PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformerscited by 78
  2. 2024D4M: Dataset Distillation via Disentangled Diffusion Modelcited by 76
  3. 2024SINGAPO: Single Image Controlled Generation of Articulated Parts in Objectscited by 66
  4. 2024SPAD : Spatially Aware Multiview Diffuserscited by 62
  5. 2024Generating CAD Code with Vision-Language Models for 3D Designscited by 61
  6. 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 60
  7. 2025OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesioncited by 60
  8. 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 57
  9. 2024Part123: Part-aware 3D Reconstruction from a Single-view Imagecited by 54
  10. 2023DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Imagecited by 48
  11. 2023Posterior Distillation Samplingcited by 45
  12. 2025Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modelingcited by 41
38 more
  1. 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
  2. 2023UniGS: Unified Representation for Image Generation and Segmentationcited by 29
  3. 2025From One to More: Contextual Part Latents for 3D Generationcited by 26
  4. 2023As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priorscited by 24
  5. 2024UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusioncited by 23
  6. 2023CAD: Photorealistic 3D Generation via Adversarial Distillationcited by 18
  7. 2025FullPart: Generating each 3D Part at Full Resolutioncited by 17
  8. 2025MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Cloudscited by 15
  9. 2024Text-to-3D Shape Generationcited by 13
  10. 2024Diffusion Models in 3D Vision: A Surveycited by 11
  11. 2024Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalizationcited by 10
  12. 2023Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Modelscited by 8
  13. 2023Advances in 3D Neural Stylization: A Surveycited by 8
  14. 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
  15. 2024Coherent 3D Scene Diffusion From a Single RGB Imagecited by 8
  16. 2025PartSDF: Part-Based Implicit Neural Representation for Composite 3D Shape Parametrization and Optimizationcited by 8
  17. 2023Spice-E : Structural Priors in 3D Diffusion using Cross-Entity Attentioncited by 7
  18. 2024Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Posescited by 6
  19. 2025MeshPad: Interactive Sketch-Conditioned Artist-Reminiscent Mesh Generation and Editingcited by 6
  20. 2026VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistencycited by 6
  21. 2024Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fieldscited by 5
  22. 2024Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Imagescited by 5
  23. 2025Toward Ambulatory Vision: Learning Visually-Grounded Active View Selectioncited by 5
  24. 2026CubePart: An Open-Vocabulary Part-Controllable 3D Generatorcited by 5
  25. 2025Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentationcited by 4
  26. 2023ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schr"odinger Bridgecited by 3
  27. 2024Occupancy-Based Dual Contouringcited by 3
  28. 2024GenUDC: High Quality 3D Mesh Generation with Unsigned Dual Contouring Representationcited by 3
  29. 2025LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and Extrapolationcited by 3
  30. 2026Deep Sketch-Based 3D Modeling: A Surveycited by 3
  31. 2024Diffusion Models for Generating Ballistic Spacecraft Trajectoriescited by 2
  32. 20243D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapescited by 2
  33. 2024JADE: Joint-aware Latent Diffusion for 3D Human Generative Modelingcited by 2
  34. 2026DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoisingcited by 2
  35. 2024Parameterize Structure with Differentiable Template for 3D Shape Generationcited by 1
  36. 2025Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generationcited by 1
  37. 2025PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenescited by 1
  38. 2025CardioComposer: Leveraging Differentiable Geometry for Compositional Control of Anatomical Diffusion Modelscited by 1

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024ShapeFusion: A 3D diffusion model for localized shape editing
  2. 2026ShapeUP: Scalable Image-Conditioned 3D Editing
  3. 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
  4. 2025HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message Passing
  5. 2025Repurposing 2D Diffusion Models for 3D Shape Completion
  6. 2024Topology-Aware Latent Diffusion for 3D Shape Generation
  7. 2023Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D
  8. 2024SC-Diff: 3D Shape Completion with Latent Diffusion Models