mlsanityData to 14 Oct 2026

ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

arXiv 2310.17994 ↗First posted 27 Oct 2023cs.CV cs.GRcited by 111

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

Abstract (arXiv)

We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose "SDS anchoring" to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Our code and data are at http://kylesargent.github.io/zeronvs/

Key facts. Cited by 111 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 37 of its 44 references that are in the map. First posted on arXiv 27 Oct 2023.

Builds on

37 of 44 references.

Closest ancestors · 12

Same direction, newest first

  1. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors30 Jun
  2. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization29 Jun
  3. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  4. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models5 Apr
  5. 20233D-aware Image Generation using 2D Diffusion Models31 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. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors6 Dec
  9. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
  10. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  11. 2022Novel View Synthesis with Diffusion Models6 Oct
  12. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 25

  1. 2020Denoising Diffusion Implicit Modelscited by 9,781
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  4. 2021Vision Transformers for Dense Predictioncited by 1,803
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  6. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  9. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  10. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  12. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
13 more
  1. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  2. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  3. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  4. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  5. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  6. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  7. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  8. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  9. 2022EpiGRAF: Rethinking training of 3D GANscited by 108
  10. 2023ATT3D: Amortized Text-to-3D Object Synthesiscited by 87
  11. 20233D generation on ImageNetcited by 47
  12. 2022Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Imagecited by 42
  13. 2023VQ3D: Learning a 3D-Aware Generative Model on ImageNetcited by 32

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 23; 2025: 51; 2026: 37.

111 papers.

Sort:

By area:

  1. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  2. 2024A Survey on 3D Gaussian Splattingcited by 224
  3. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 144
  4. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  5. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representationcited by 123
  6. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 118
  7. 2025Cameras as Relative Positional Encodingcited by 105
  8. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 99
  9. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  10. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 67
  11. 2025Bolt3D: Generating 3D Scenes in Secondscited by 59
  12. 2025SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generationcited by 48
38 more
  1. 2025World-in-World: World Models in a Closed-Loop Worldcited by 47
  2. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  3. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 41
  4. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 40
  5. 2025GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priorscited by 38
  6. 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
  7. 2025Matrix-3D: Omnidirectional Explorable 3D World Generationcited by 35
  8. 2024MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Modelcited by 32
  9. 2025Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentationcited by 31
  10. 2025FlowR: Flowing from Sparse to Dense 3D Reconstructionscited by 28
  11. 2026VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Controlcited by 28
  12. 2024Feat2GS: Probing Visual Foundation Models with Gaussian Splattingcited by 27
  13. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  14. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 20
  15. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  16. 2025AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletonscited by 18
  17. 2024SplatFormer: Point Transformer for Robust 3D Gaussian Splattingcited by 16
  18. 2024Novel View Synthesis with Pixel-Space Diffusion Modelscited by 16
  19. 2024Using Diffusion Priors for Video Amodal Segmentationcited by 16
  20. 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidancecited by 16
  21. 2024X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarioscited by 14
  22. 2025SPATIALGEN: Layout-guided 3D Indoor Scene Generationcited by 14
  23. 2025A Recipe for Generating 3D Worlds From a Single Imagecited by 13
  24. 2025Dynamic View Synthesis as an Inverse Problemcited by 12
  25. 2025High-Fidelity Novel View Synthesis via Splatting-Guided Diffusioncited by 11
  26. 2025Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Viewscited by 11
  27. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 11
  28. 2024MOVIS: Enhancing Multi-Object Novel View Synthesis for Indoor Scenescited by 10
  29. 2025Can Video Diffusion Model Reconstruct 4D Geometry?cited by 10
  30. 2025Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversioncited by 10
  31. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Priorcited by 10
  32. 2024MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction: Methods and Resultscited by 9
  33. 2025OmniCam: Unified Multimodal Video Generation via Camera Controlcited by 9
  34. 2025Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creationcited by 9
  35. 2024How to Use Diffusion Priors under Sparse Views?cited by 8
  36. 2024FoundHand: Large-Scale Domain-Specific Learning for Controllable Hand Image Generationcited by 8
  37. 2024CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Imagecited by 7
  38. 2026NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstructioncited by 7

50 most cited of 111 All 111 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 20243D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance
  2. 2024MegaScenes: Scene-Level View Synthesis at Scale
  3. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
  4. 2024FSViewFusion: Few-Shots View Generation of Novel Objects
  5. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
  6. 2023iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis
  7. 2023ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models
  8. 2026OrbitNVS: Harnessing Video Diffusion Priors for Novel View Synthesis