mlsanityData to 7 Oct 2026

Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation

arXiv 2302.00190 ↗First posted 1 Feb 2023cs.CV cs.GRcited by 27

Not on the map. Why?

Abstract (arXiv)

This paper presents a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets. Then, we design a pair of neural networks: a diffusion-based generator to produce diverse shapes in the form of the coarse coefficient volumes and a detail predictor to produce compatible detail coefficient volumes for introducing fine structures and details. Further, we may jointly train an encoder network to learn a latent space for inverting shapes, allowing us to enable a rich variety of whole-shape and region-aware shape manipulations. Both quantitative and qualitative experimental results manifest the compelling shape generation, inversion, and manipulation capabilities of our approach over the state-of-the-art methods.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 67 of its 90 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

67 of 90 references.

References · 67

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  9. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  10. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  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. 2020Neural Sparse Voxel Fieldscited by 959
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  3. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  4. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  6. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  7. 2021Designing an Encoder for StyleGAN Image Manipulationcited by 542
  8. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  9. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  10. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  11. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  12. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  13. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  14. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  15. 2021GAN Inversion: A Surveycited by 366
  16. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  17. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  18. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  19. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  20. 2020Learning Gradient Fields for Shape Generationcited by 245
  21. 2020Semantic Photo Manipulation with a Generative Image Priorcited by 178
  22. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  23. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  24. 2022ShapeFormer: Transformer-based Shape Completion via Sparse Representationcited by 106
  25. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  26. 2020SoftFlow: Probabilistic Framework for Normalizing Flow on Manifoldscited by 97
  27. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  28. 2020DualSDF: Semantic Shape Manipulation using a Two-Level Representationcited by 82
  29. 2021Unsupervised 3D Shape Completion through GAN Inversioncited by 70
  30. 2022Towards Implicit Text-Guided 3D Shape Generationcited by 68
  31. 2021Deep Implicit Moving Least-Squares Functions for 3D Reconstructioncited by 67
  32. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  33. 2021ACORN: Adaptive Coordinate Networks for Neural Scene Representationcited by 64
  34. 20213D Shape Generation with Grid-based Implicit Functionscited by 48
  35. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  36. 2020Progressive Point Cloud Deconvolution Generation Networkcited by 46
  37. 2020D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Imagescited by 42
  38. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 6; 2026: 11.

27 papers.

Sort:

By area:

  1. 2024Towards Realistic Scene Generation with LiDAR Diffusion Modelscited by 67
  2. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulationcited by 66
  3. 2023Texture Generation on 3D Meshes with Point-UV Diffusioncited by 63
  4. 2023InstructP2P: Learning to Edit 3D Point Clouds with Text Instructionscited by 14
  5. 2026LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistencycited by 9
  6. 2023Advances in 3D Neural Stylization: A Surveycited by 8
  7. 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
  8. 2024Generating 3D House Wireframes with Semanticscited by 8
  9. 2023Spatial-Frequency U-Net for Denoising Diffusion Probabilistic Modelscited by 7
  10. 2025CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generationcited by 7
  11. 2024Part-aware Shape Generation with Latent 3D Diffusion of Neural Voxel Fieldscited by 5
  12. 2025SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materialscited by 5
15 more
  1. 2026PEGAsus: 3D Personalization of Geometry and Appearancecited by 5
  2. 2026Deep Sketch-Based 3D Modeling: A Surveycited by 3
  3. 2026Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimationcited by 3
  4. 2025WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generationcited by 2
  5. 2026EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentationcited by 2
  6. 2024View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selectioncited by 1
  7. 2025B-Rep Distance Functions (BR-DF): How to Represent a B-Rep Model by Volumetric Distance Functions?cited by 1
  8. 2026Spectral Regularization for Diffusion Modelscited by 1
  9. 2026High-Fidelity Medical Shape Generation via Skeletal Latent Diffusioncited by 1
  10. 2025WonderVerse: Extendable 3D Scene Generation with Video Generative Modelscited by 0
  11. 20253D Shape Generation: A Surveycited by 0
  12. 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representationcited by 0
  13. 2026Fourier-Latent Diffusion for Constrained Generation of Triply Periodic Minimal Surfacescited by 0
  14. 2026BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D Generationcited by 0
  15. 2026DiDE:Direct Injection with Color-Texture DEcoupling for 3D Stylizationcited by 0