mlsanityData to 14 Oct 2026

DiffComplete: Diffusion-based Generative 3D Shape Completion

arXiv 2306.16329 ↗First posted 28 Jun 2023cs.CVcited by 35

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

Abstract (arXiv)

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete by casting shape completion as a generative task conditioned on the incomplete shape. Our key designs are two-fold. First, we devise a hierarchical feature aggregation mechanism to inject conditional features in a spatially-consistent manner. So, we can capture both local details and broader contexts of the conditional inputs to control the shape completion. Second, we propose an occupancy-aware fusion strategy in our model to enable the completion of multiple partial shapes and introduce higher flexibility on the input conditions. DiffComplete sets a new SOTA performance (e.g., 40% decrease on l_1 error) on two large-scale 3D shape completion benchmarks. Our completed shapes not only have a realistic outlook compared with the deterministic methods but also exhibit high similarity to the ground truths compared with the probabilistic alternatives. Further, DiffComplete has strong generalizability on objects of entirely unseen classes for both synthetic and real data, eliminating the need for model re-training in various applications.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 54 of its 86 references that are in the map. First posted on arXiv 28 Jun 2023.

Builds on

54 of 86 references.

Closest ancestors · 8

Same direction, newest first

  1. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  2. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  3. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusion2 Dec
  4. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models1 Dec
  5. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions24 Nov
  6. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan
  8. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
34 more
  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  3. 2020Convolutional Occupancy Networkscited by 761
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  5. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  6. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  7. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  8. 2021Neural RGB-D Surface Reconstructioncited by 313
  9. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  10. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  11. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  12. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  13. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 175
  14. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  15. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  16. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  17. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  18. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  19. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  20. 2019SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scanscited by 77
  21. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  22. 2020Fast and Robust Iterative Closest Pointcited by 67
  23. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  24. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  25. 2020Multimodal Shape Completion via Conditional Generative Adversarial Networkscited by 61
  26. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  27. 2018Scan2Mesh: From Unstructured Range Scans to 3D Meshescited by 51
  28. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  29. 2020SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scanscited by 34
  30. 2017Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lightingcited by 31
  31. 2019Few-Shot Generalization for Single-Image 3D Reconstruction via Priorscited by 25
  32. 2022PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categoriescited by 21
  33. 2023TriVol: Point Cloud Rendering via Triple Volumescited by 16
  34. 2022Probabilistic Implicit Scene Completioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 11; 2025: 8; 2026: 14.

35 papers.

Sort:

By area:

  1. 2023DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generationcited by 110
  2. 2025HoloPart: Generative 3D Part Amodal Segmentationcited by 60
  3. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 54
  4. 2024R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detectioncited by 45
  5. 2025Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidancecited by 45
  6. 2025SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Modelcited by 17
  7. 2024SC-Diff: 3D Shape Completion with Latent Diffusion Modelscited by 10
  8. 2026LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistencycited by 9
  9. 2024DNF: Unconditional 4D Generation with Dictionary-based Neural Fieldscited by 8
  10. 2024ComPC: Completing a 3D Point Cloud with 2D Diffusion Priorscited by 6
  11. 2024Cultural Heritage 3D Reconstruction with Diffusion Networkscited by 4
  12. 2026Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priorscited by 4
23 more
  1. 2024Diff-PCC: Diffusion-based Neural Compression for 3D Point Cloudscited by 2
  2. 2024Self-supervised Shape Completion via Involution and Implicit Correspondencescited by 2
  3. 2024IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Imagescited by 1
  4. 2024Diffusion-Occ: 3D Point Cloud Completion via Occupancy Diffusioncited by 1
  5. 2025Surf2CT: Cascaded 3D Flow Matching Models for Torso 3D CT Synthesis from Skin Surfacecited by 1
  6. 2025BridgeShape: Latent Diffusion Schr"odinger Bridge for 3D Shape Completioncited by 1
  7. 2026VIAFormer: Voxel-Image Alignment Transformer for High-Fidelity Voxel Refinementcited by 1
  8. 2026Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flowcited by 1
  9. 2026I2PRef: Image-Driven Point Completion with Iterative Refinementcited by 1
  10. 2023NeuSD: Surface Completion with Multi-View Text-to-Image Diffusioncited by 0
  11. 2024Diverse Part Synthesis for 3D Shape Creationcited by 0
  12. 2024RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Modelscited by 0
  13. 2025Online Estimation of Table-Top Grown Strawberry Mass in Field Conditions with Occlusionscited by 0
  14. 2025OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Cloudscited by 0
  15. 2026Enhanced Mixture 3D CGAN for Completion and Generation of 3D Objectscited by 0
  16. 2026From Synthetic Data to Real Restorations: Diffusion Model for Patient-specific Dental Crown Completioncited by 0
  17. 2026Generative Shape Reconstruction with Geometry-Guided Langevin Dynamicscited by 0
  18. 2026Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touchcited by 0
  19. 2026DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Modelscited by 0
  20. 2026CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domaincited by 0
  21. 2026Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generationcited by 0
  22. 2026Restore3D: Breathing Life into Broken Objects with Shape and Texture Restorationcited by 0
  23. 2026Trajectory-Level Mode Guidance for Controllable Diffusion-Based Multi-Robot Motion Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
  2. 2025Repurposing 2D Diffusion Models for 3D Shape Completion
  3. 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
  4. 2025GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion
  5. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
  6. 2022A Structure-Guided Diffusion Model for Large-Hole Image Completion
  7. 2025Geometry-Aware Diffusion Models for Multiview Scene Inpainting
  8. 2024Diffusion Models in 3D Vision: A Survey