mlsanityData to 7 Oct 2026

Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion

arXiv 2511.17932 ↗First posted 22 Nov 2025cs.CV cs.GRcited by 4

Not on the map. Why?

Abstract (arXiv)

Given just a few glimpses of a scene, can you imagine the movie playing out as the camera glides through it? That's the lens we take on sparse-input novel view synthesis, not only as filling spatial gaps between widely spaced views, but also as completing a natural video unfolding through space. We recast the task as test-time natural video completion, using powerful priors from pretrained video diffusion models to hallucinate plausible in-between views. Our zero-shot, generation-guided framework produces pseudo views at novel camera poses, modulated by an uncertainty-aware mechanism for spatial coherence. These synthesized frames densify supervision for 3D Gaussian Splatting (3D-GS) for scene reconstruction, especially in under-observed regions. An iterative feedback loop lets 3D geometry and 2D view synthesis inform each other, improving both the scene reconstruction and the generated views. The result is coherent, high-fidelity renderings from sparse inputs without any scene-specific training or fine-tuning. On LLFF, DTU, DL3DV, and MipNeRF-360, our method significantly outperforms strong 3D-GS baselines under extreme sparsity.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 57 of its 67 references that are in the map. First posted on arXiv 22 Nov 2025.

Builds on

57 of 67 references.

References · 57

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  6. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  7. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  8. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  9. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  10. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  11. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
38 more
  1. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  5. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  7. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  9. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  10. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  11. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  12. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  13. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
  14. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 568
  15. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  16. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  17. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  18. 2023Universal Guidance for Diffusion Modelscited by 426
  19. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  20. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  21. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  22. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 290
  23. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  24. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  25. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  26. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  27. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  28. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  29. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  30. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  31. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  32. 2024Training-free Camera Control for Video Generationcited by 119
  33. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  34. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  35. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  36. 2024CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussianscited by 62
  37. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  38. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026R2S-EGO: Dual-Proxy Refinement for Sparse-Capture Real-to-Simcited by 1
  2. 2026FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priorscited by 0
  3. 2026Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understandingcited by 0
  4. 2026VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026FrameCrafter: Novel View Synthesis as Video Completion
  2. 2026RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation
  3. 2026Stabilizing Camera-Controlled Novel View Synthesis at Inference Time
  4. 2026DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images
  5. 2025SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations
  6. 2025Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
  7. 2025Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion
  8. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction