mlsanityData to 14 Oct 2026

UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion

arXiv 2404.06851 ↗First posted 10 Apr 2024cs.CVcited by 23

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

Abstract (arXiv)

Diffusion models have shown remarkable results for image generation, editing and inpainting. Recent works explore diffusion models for 3D shape generation with neural implicit functions, i.e., signed distance function and occupancy function. However, they are limited to shapes with closed surfaces, which prevents them from generating diverse 3D real-world contents containing open surfaces. In this work, we present UDiFF, a 3D diffusion model for unsigned distance fields (UDFs) which is capable to generate textured 3D shapes with open surfaces from text conditions or unconditionally. Our key idea is to generate UDFs in spatial-frequency domain with an optimal wavelet transformation, which produces a compact representation space for UDF generation. Specifically, instead of selecting an appropriate wavelet transformation which requires expensive manual efforts and still leads to large information loss, we propose a data-driven approach to learn the optimal wavelet transformation for UDFs. We evaluate UDiFF to show our advantages by numerical and visual comparisons with the latest methods on widely used benchmarks. Page: https://weiqi-zhang.github.io/UDiFF.

Key facts. Cited by 23 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 70 of its 81 references that are in the map. First posted on arXiv 10 Apr 2024.

Builds on

70 of 81 references.

Closest ancestors · 11

Same direction, newest first

  1. 2023GeoDream: Disentangling 2D and Geometric Priors for High-Fidelity and Consistent 3D Generation29 Nov
  2. 2023SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation21 Mar
  3. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Models20 Mar
  4. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generation9 Mar
  5. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  6. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  7. 20223D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models1 Dec
  8. 20223D Neural Field Generation using Triplane Diffusion30 Nov
  9. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions24 Nov
  10. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  11. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 59

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  7. 2022Generative Adversarial Networkscited by 5,627
  8. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  11. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  12. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
38 more
  1. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  3. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  4. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  5. 2020Convolutional Occupancy Networkscited by 761
  6. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  7. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  8. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 488
  9. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  10. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  11. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  12. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  13. 2020Learning Gradient Fields for Shape Generationcited by 245
  14. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  15. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  16. 2020Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfacescited by 147
  17. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  18. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 130
  19. 2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
  20. 2020Deep Fashion3D: A Dataset and Benchmark for 3D Garment Reconstruction from Single Imagescited by 103
  21. 2021MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networkscited by 76
  22. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  23. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
  24. 2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
  25. 2018Robust Watertight Manifold Surface Generation Method for ShapeNet Modelscited by 59
  26. 2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
  27. 2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
  28. 2020Adversarial Generation of Continuous Implicit Shape Representationscited by 46
  29. 2020Progressive Point Cloud Deconvolution Generation Networkcited by 46
  30. 20223D Shape Reconstruction from 2D Images with Disentangled Attribute Flowcited by 45
  31. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  32. 2023NeUDF: Leaning Neural Unsigned Distance Fields with Volume Renderingcited by 41
  33. 2023Towards Better Gradient Consistency for Neural Signed Distance Functions via Level Set Alignmentcited by 39
  34. 2022Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformercited by 38
  35. 2022Fast Learning Radiance Fields by Shooting Much Fewer Rayscited by 38
  36. 2022NeAF: Learning Neural Angle Fields for Point Normal Estimationcited by 38
  37. 2023Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matchingcited by 37
  38. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 37

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 11; 2025: 9; 2026: 3.

23 papers.

Sort:

By area:

  1. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  2. 2024DiffGS: Functional Gaussian Splatting Diffusioncited by 51
  3. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  4. 2024Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assemblycited by 35
  5. 2024Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesiscited by 18
  6. 2024VRP-UDF: Towards Unbiased Learning of Unsigned Distance Functions from Multi-view Images with Volume Rendering Priorscited by 17
  7. 2024Fast Learning of Signed Distance Functions from Noisy Point Clouds via Noise to Noise Mappingcited by 15
  8. 2025MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstructioncited by 15
  9. 2025NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstructioncited by 12
  10. 2024Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodingscited by 10
  11. 2026MoRe: Motion-aware Feed-forward 4D Reconstruction Transformercited by 9
  12. 2025UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mappingcited by 8
11 more
  1. 2024Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstructioncited by 7
  2. 2024A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functionscited by 7
  3. 2025Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformationcited by 7
  4. 2025GAP: Gaussianize Any Point Clouds with Text Guidancecited by 7
  5. 2025U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matchingcited by 3
  6. 20243D-WAG: Hierarchical Wavelet-Guided Autoregressive Generation for High-Fidelity 3D Shapescited by 2
  7. 2025A Mesh Is Worth 512 Numbers: Spectral-domain Diffusion Modeling for High-dimension Shape Generationcited by 1
  8. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  9. 2026GaussianGrow: Geometry-aware Gaussian Growing from 3D Point Clouds with Text Guidancecited by 1
  10. 2025MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstructioncited by 0
  11. 2026DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models
  2. 2023Single Mesh Diffusion Models with Field Latents for Texture Generation
  3. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
  4. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
  5. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
  6. 2025DoubleDiffusion: Combining Heat Diffusion with Denoising Diffusion for Texture Generation on 3D Meshes
  7. 2023Mosaic-SDF for 3D Generative Models
  8. 2023Breathing New Life into 3D Assets with Generative Repainting