mlsanityData to 7 Oct 2026

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

arXiv 2402.12712 ↗First posted 20 Feb 2024cs.CVcited by 94

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

Abstract (arXiv)

This paper presents a neural architecture MVDiffusion++ for 3D object reconstruction that synthesizes dense and high-resolution views of an object given one or a few images without camera poses. MVDiffusion++ achieves superior flexibility and scalability with two surprisingly simple ideas: 1) A ``pose-free architecture'' where standard self-attention among 2D latent features learns 3D consistency across an arbitrary number of conditional and generation views without explicitly using camera pose information; and 2) A ``view dropout strategy'' that discards a substantial number of output views during training, which reduces the training-time memory footprint and enables dense and high-resolution view synthesis at test time. We use the Objaverse for training and the Google Scanned Objects for evaluation with standard novel view synthesis and 3D reconstruction metrics, where MVDiffusion++ significantly outperforms the current state of the arts. We also demonstrate a text-to-3D application example by combining MVDiffusion++ with a text-to-image generative model. The project page is at https://mvdiffusion-plusplus.github.io.

Key facts. Cited by 94 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 38 of its 46 references that are in the map. First posted on arXiv 20 Feb 2024.

Builds on

38 of 46 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation2 Dec
  2. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion14 Nov
  3. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model23 Oct
  4. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  5. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  6. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  7. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors30 Jun
  8. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  10. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec

Other references · 28

  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. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  7. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  12. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
16 more
  1. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  2. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  3. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  4. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  5. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  6. 2023Common Diffusion Noise Schedules and Sample Steps are Flawedcited by 308
  7. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  8. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  9. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  10. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  11. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  12. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  13. 2016Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervisioncited by 106
  14. 2023LEAP: Liberate Sparse-view 3D Modeling from Camera Posescited by 65
  15. 2022FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstructioncited by 19
  16. 2023Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstructioncited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 44; 2025: 37; 2026: 13.

94 papers.

Sort:

By area:

  1. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  2. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  3. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
  4. 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 111
  5. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 99
  6. 2024Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Modelscited by 99
  7. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  8. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
  9. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  10. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  11. 2024Controlling Space and Time with Diffusion Modelscited by 65
  12. 2024PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Modelscited by 60
38 more
  1. 2024ComboVerse: Compositional 3D Assets Creation Using Spatially-Aware Diffusion Guidancecited by 59
  2. 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
  3. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  4. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  5. 2024Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Imagescited by 34
  6. 2024An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusioncited by 34
  7. 2024Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusioncited by 31
  8. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputscited by 29
  9. 2025MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusioncited by 28
  10. 2024AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animationcited by 25
  11. 2024Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Modelscited by 24
  12. 2024Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attentioncited by 24
  13. 2024PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshingcited by 23
  14. 2025UniTEX: Universal High Fidelity Generative Texturing for 3D Shapescited by 23
  15. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  16. 2024TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshescited by 20
  17. 2025RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesiscited by 20
  18. 2024GGS: Generalizable Gaussian Splatting for Lane Switching in Autonomous Drivingcited by 17
  19. 20243D Mesh Editing using Masked LRMscited by 17
  20. 2025UnCommon Objects in 3Dcited by 17
  21. 2024Gen-3Diffusion: Realistic Image-to-3D Generation via 2D & 3D Diffusion Synergycited by 16
  22. 2025LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fieldscited by 16
  23. 2024PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verifycited by 14
  24. 2025Survey of Video Diffusion Models: Foundations, Implementations, and Applicationscited by 14
  25. 2024A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generationcited by 13
  26. 2025VideoPanda: Video Panoramic Diffusion with Multi-view Attentioncited by 13
  27. 2025Edit360: 2D Image Edits to 3D Assets from Any Anglecited by 13
  28. 2024Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detailcited by 12
  29. 2024Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curationcited by 12
  30. 2024MvDrag3D: Drag-based Creative 3D Editing via Multi-view Generation-Reconstruction Priorscited by 12
  31. 2024Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Secondscited by 11
  32. 2024LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priorscited by 11
  33. 2025Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editingcited by 11
  34. 2024Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Modelscited by 10
  35. 2024Edify 3D: Scalable High-Quality 3D Asset Generationcited by 10
  36. 2025Conditional Panoramic Image Generation via Masked Autoregressive Modelingcited by 9
  37. 2025SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstructioncited by 8
  38. 2024FlowDreamer: Exploring High Fidelity Text-to-3D Generation via Rectified Flowcited by 7

50 most cited of 94 All 94 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View
  2. 2024MVD2: Efficient Multiview 3D Reconstruction for Multiview Diffusion
  3. 2023Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views
  4. 2024MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model
  5. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
  6. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
  7. 2024MultiDiff: Consistent Novel View Synthesis from a Single Image
  8. 2022Novel View Synthesis with Diffusion Models