mlsanityData to 14 Oct 2026

Wonder3D: Single Image to 3D using Cross-Domain Diffusion

arXiv 2310.15008 ↗First posted 23 Oct 2023cs.CVcited by 689

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

Abstract (arXiv)

In this work, we introduce Wonder3D, a novel method for efficiently generating high-fidelity textured meshes from single-view images.Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of image-to-3D tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure consistency, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a geometry-aware normal fusion algorithm that extracts high-quality surfaces from the multi-view 2D representations. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and reasonably good efficiency compared to prior works.

Key facts. Cited by 689 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 68 of its 84 references that are in the map. First posted on arXiv 23 Oct 2023.

Builds on

68 of 84 references.

Closest ancestors · 40

Same direction, newest first

  1. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  2. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  3. 2023HoloFusion: Towards Photo-realistic 3D Generative Modeling28 Aug
  4. 2023IT3D: Improved Text-to-3D Generation with Explicit View Synthesis22 Aug
  5. 2023HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation30 Jul
  6. 2023Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation26 Jul
  7. 2023AutoDecoding Latent 3D Diffusion Models7 Jul
  8. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors30 Jun
  9. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  10. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data13 Jun
  11. 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views6 Jun
  12. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
28 more
  1. 2023Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields19 May
  2. 2023TextMesh: Generation of Realistic 3D Meshes From Text Prompts24 Apr
  3. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models21 Apr
  4. 2023NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models19 Apr
  5. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction13 Apr
  6. 2023Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images13 Apr
  7. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models5 Apr
  8. 20233D-aware Image Generation using 2D Diffusion Models31 Mar
  9. 2023Consistent View Synthesis with Pose-Guided Diffusion Models30 Mar
  10. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior24 Mar
  11. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  13. 2023Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation14 Mar
  14. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generation9 Mar
  15. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  16. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  17. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion12 Dec
  18. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models12 Dec
  19. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors6 Dec
  20. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusion2 Dec
  21. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  22. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Views29 Nov
  23. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  24. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation17 Nov
  25. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  26. 2022Novel View Synthesis with Diffusion Models6 Oct
  27. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep
  28. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 28

  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. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  7. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  8. 2022Diffusion Models in Vision: A Surveycited by 1,015
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  10. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  11. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  12. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
16 more
  1. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  2. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  3. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  4. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  5. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 212
  6. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 199
  7. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  8. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 180
  9. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  10. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  11. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  12. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  13. 2023Anything-3D: Towards Single-view Anything Reconstruction in the Wildcited by 92
  14. 2021Adaptive Surface Normal Constraint for Depth Estimationcited by 43
  15. 2023DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Modelcited by 43
  16. 2022TORE: Token Reduction for Efficient Human Mesh Recovery with Transformercited by 41

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 37; 2024: 257; 2025: 227; 2026: 168.

689 papers.

Sort:

By area:

  1. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  2. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  3. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  4. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  5. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  6. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 356
  7. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 335
  8. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  9. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
  10. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  11. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 257
  12. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 215
38 more
  1. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  2. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  3. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  4. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
  5. 2024Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Predictioncited by 166
  6. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  7. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  8. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 154
  9. 2024GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generationcited by 153
  10. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 144
  11. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 144
  12. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  13. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusioncited by 140
  14. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  15. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 135
  16. 2024Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiTcited by 132
  17. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 125
  18. 2023Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Modelscited by 123
  19. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 123
  20. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117
  21. 2024Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Controlcited by 117
  22. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 117
  23. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  24. 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 112
  25. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 110
  26. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 106
  27. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generationcited by 104
  28. 2024STAG4D: Spatial-Temporal Anchored Generative 4D Gaussianscited by 102
  29. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 101
  30. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
  31. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 100
  32. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Modelscited by 100
  33. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 99
  34. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 99
  35. 2024PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Acceleratorcited by 97
  36. 2024EscherNet: A Generative Model for Scalable View Synthesiscited by 95
  37. 2024MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstructioncited by 95
  38. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 92

50 most cited of 689 All 689 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  2. 2023Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
  3. 2024MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View
  4. 2023Consistent Mesh Diffusion
  5. 2023DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
  6. 2023MVDD: Multi-View Depth Diffusion Models
  7. 2024DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D Generation
  8. 2024Coherent 3D Scene Diffusion From a Single RGB Image