mlsanityData to 7 Oct 2026

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising

arXiv 2402.18842 ↗First posted 29 Feb 2024cs.CVcited by 14

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

Abstract (arXiv)

Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads to challenges in maintaining multiple-view consistency. To address this, we introduce ViewFusion, a novel, training-free algorithm that can be seamlessly integrated into existing pre-trained diffusion models. Our approach adopts an auto-regressive method that implicitly leverages previously generated views as context for the next view generation, ensuring robust multi-view consistency during the novel-view generation process. Through a diffusion process that fuses known-view information via interpolated denoising, our framework successfully extends single-view conditioned models to work in multiple-view conditional settings without any additional fine-tuning. Extensive experimental results demonstrate the effectiveness of ViewFusion in generating consistent and detailed novel views.

Key facts. Cited by 14 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 74 of its 87 references that are in the map. First posted on arXiv 29 Feb 2024.

Builds on

74 of 87 references.

Closest ancestors · 33

Same direction, newest first

  1. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesis12 Oct
  2. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models4 Oct
  3. 2023HoloFusion: Towards Photo-realistic 3D Generative Modeling28 Aug
  4. 2023AutoDecoding Latent 3D Diffusion Models7 Jul
  5. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  6. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data13 Jun
  7. 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views6 Jun
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  9. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models21 Apr
  10. 2023NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models19 Apr
  11. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction13 Apr
  12. 2023Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images13 Apr
21 more
  1. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models5 Apr
  2. 20233D-aware Image Generation using 2D Diffusion Models31 Mar
  3. 2023Consistent View Synthesis with Pose-Guided Diffusion Models30 Mar
  4. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Images29 Mar
  5. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior24 Mar
  6. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation24 Mar
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  8. 20233DGen: Triplane Latent Diffusion for Textured Mesh Generation9 Mar
  9. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  10. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  11. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion12 Dec
  12. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models12 Dec
  13. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors6 Dec
  14. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusion2 Dec
  15. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  16. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Views29 Nov
  17. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  18. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation17 Nov
  19. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  20. 2022Novel View Synthesis with Diffusion Models6 Oct
  21. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 41

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  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. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  7. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  8. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  9. 2014Conditional Generative Adversarial Netscited by 2,152
  10. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  11. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  12. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
29 more
  1. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  2. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  3. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  4. 2016Generative Adversarial Text to Image Synthesiscited by 735
  5. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  6. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  7. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  8. 2021Neural Fields in Visual Computing and Beyondcited by 539
  9. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  10. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  11. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  12. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  13. 2020State of the Art on Neural Renderingcited by 276
  14. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  15. 2023DreamBooth3D: Subject-Driven Text-to-3D Generationcited by 235
  16. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  17. 2023MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusioncited by 210
  18. 2023MeshDiffusion: Score-based Generative 3D Mesh Modelingcited by 198
  19. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  20. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  21. 2023HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusioncited by 152
  22. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  23. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  24. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  25. 2020SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Imagescited by 68
  26. 2023ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusioncited by 65
  27. 2018Learning View Priors for Single-view 3D Reconstructioncited by 35
  28. 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetcited by 32
  29. 2022Single-view 3D Mesh Reconstruction for Seen and Unseen Categoriescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 3.

14 papers.

Sort:

By area:

  1. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  2. 2025MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusioncited by 28
  3. 2024Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filteringcited by 9
  4. 2025MVGBench: Comprehensive Benchmark for Multi-view Generation Modelscited by 9
  5. 2024Benchmarking and Learning Multi-Dimensional Quality Evaluator for Text-to-3D Generationcited by 7
  6. 2025WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Explorationcited by 7
  7. 2025Geometric Consistency Refinement for Single Image Novel View Synthesis via Test-Time Adaptation of Diffusion Modelscited by 2
  8. 2025ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstructioncited by 2
  9. 2025Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metriccited by 2
  10. 2025StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Spacecited by 2
  11. 2024Consistency of Compositional Generalization across Multiple Levelscited by 1
  12. 2026ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splattingcited by 1
2 more
  1. 2026SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertioncited by 0
  2. 2026RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
  2. 2024FSViewFusion: Few-Shots View Generation of Novel Objects
  3. 2025Sphinx: Efficiently Serving Novel View Synthesis using Regression-Guided Selective Refinement
  4. 2024VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
  5. 2024MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning
  6. 2026Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion
  7. 2025Coupled Diffusion Sampling for Training-Free Multi-View Image Editing
  8. 2025WAVE: Warp-Based View Guidance for Consistent Novel View Synthesis Using a Single Image