mlsanityData to 7 Oct 2026

Consistent123: Improve Consistency for One Image to 3D Object Synthesis

arXiv 2310.08092 ↗First posted 12 Oct 2023cs.CVcited by 84

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

Abstract (arXiv)

Large image diffusion models enable novel view synthesis with high quality and excellent zero-shot capability. However, such models based on image-to-image translation have no guarantee of view consistency, limiting the performance for downstream tasks like 3D reconstruction and image-to-3D generation. To empower consistency, we propose Consistent123 to synthesize novel views simultaneously by incorporating additional cross-view attention layers and the shared self-attention mechanism. The proposed attention mechanism improves the interaction across all synthesized views, as well as the alignment between the condition view and novel views. In the sampling stage, such architecture supports simultaneously generating an arbitrary number of views while training at a fixed length. We also introduce a progressive classifier-free guidance strategy to achieve the trade-off between texture and geometry for synthesized object views. Qualitative and quantitative experiments show that Consistent123 outperforms baselines in view consistency by a large margin. Furthermore, we demonstrate a significant improvement of Consistent123 on varying downstream tasks, showing its great potential in the 3D generation field. The project page is available at consistent-123.github.io.

Key facts. Cited by 84 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 40 of its 42 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

40 of 42 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  2. 20233D-aware Image Generation using 2D Diffusion Models31 Mar
  3. 2023Consistent View Synthesis with Pose-Guided Diffusion Models30 Mar
  4. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  5. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  6. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  7. 2022Novel View Synthesis with Diffusion Models6 Oct
  8. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep
  9. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  11. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  12. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
19 more
  1. 2022Video Diffusion Modelscited by 2,280
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  3. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  5. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  6. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  7. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  8. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  10. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  11. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  12. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  13. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  14. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  15. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  16. 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
  17. 20233D generation on ImageNetcited by 47
  18. 2022RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesiscited by 33
  19. 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetcited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 15; 2024: 43; 2025: 23; 2026: 3.

84 papers.

Sort:

By area:

  1. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  2. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  3. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  4. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
  5. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  6. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  7. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  8. 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generationcited by 84
  9. 2023Free3D: Consistent Novel View Synthesis without 3D Representationcited by 72
  10. 2024Scaling Mesh Generation via Compressive Tokenizationcited by 71
  11. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  12. 2024SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglementcited by 65
38 more
  1. 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Modelscited by 64
  2. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 62
  3. 2024Learning the 3D Fauna of the Webcited by 58
  4. 2023ViVid-1-to-3: Novel View Synthesis with Video Diffusion Modelscited by 57
  5. 2024Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructioncited by 56
  6. 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
  7. 2024PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidancecited by 47
  8. 2024REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignmentcited by 45
  9. 2025SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generationcited by 44
  10. 2024GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generationcited by 35
  11. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  12. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  13. 2023Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Viewscited by 32
  14. 2024DragAPart: Learning a Part-Level Motion Prior for Articulated Objectscited by 32
  15. 2024Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamicscited by 28
  16. 2023Stable Score Distillation for High-Quality 3D Generationcited by 27
  17. 2023HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3Dcited by 27
  18. 2023DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesiscited by 26
  19. 2024Garment3DGen: 3D Garment Stylization and Texture Generationcited by 26
  20. 2025DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundnesscited by 24
  21. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  22. 2024MVD2: Efficient Multiview 3D Reconstruction for Multiview Diffusioncited by 22
  23. 2023DreamPropeller: Supercharge Text-to-3D Generation with Parallel Samplingcited by 20
  24. 2024Diffusion Time-step Curriculum for One Image to 3D Generationcited by 20
  25. 2024Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabricationcited by 19
  26. 2023DreamComposer: Controllable 3D Object Generation via Multi-View Conditionscited by 18
  27. 2024GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Qualitycited by 17
  28. 20244Dynamic: Text-to-4D Generation with Hybrid Priorscited by 15
  29. 2024ViewFusion: Towards Multi-View Consistency via Interpolated Denoisingcited by 14
  30. 2025Simulating the Real World: A Unified Survey of Multimodal Generative Modelscited by 14
  31. 2024Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embeddingcited by 13
  32. 2024LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priorscited by 11
  33. 2024Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimationcited by 10
  34. 20243DEgo: 3D Editing on the Go!cited by 10
  35. 2024Edify 3D: Scalable High-Quality 3D Asset Generationcited by 10
  36. 2024Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehiclescited by 10
  37. 2024Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filteringcited by 9
  38. 2024HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Modelcited by 9

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
  2. 2025AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction
  3. 2025WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image
  4. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models
  5. 2023ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion
  6. 2025DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
  7. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
  8. 2025ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization