mlsanityData to 7 Oct 2026

3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors

arXiv 2410.16266 ↗First posted 21 Oct 2024cs.CV cs.AIcited by 106

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

Abstract (arXiv)

Novel-view synthesis aims to generate novel views of a scene from multiple input images or videos, and recent advancements like 3D Gaussian splatting (3DGS) have achieved notable success in producing photorealistic renderings with efficient pipelines. However, generating high-quality novel views under challenging settings, such as sparse input views, remains difficult due to insufficient information in under-sampled areas, often resulting in noticeable artifacts. This paper presents 3DGS-Enhancer, a novel pipeline for enhancing the representation quality of 3DGS representations. We leverage 2D video diffusion priors to address the challenging 3D view consistency problem, reformulating it as achieving temporal consistency within a video generation process. 3DGS-Enhancer restores view-consistent latent features of rendered novel views and integrates them with the input views through a spatial-temporal decoder. The enhanced views are then used to fine-tune the initial 3DGS model, significantly improving its rendering performance. Extensive experiments on large-scale datasets of unbounded scenes demonstrate that 3DGS-Enhancer yields superior reconstruction performance and high-fidelity rendering results compared to state-of-the-art methods. The project webpage is https://xiliu8006.github.io/3DGS-Enhancer-project .

Key facts. Cited by 106 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 41 of its 46 references that are in the map. First posted on arXiv 21 Oct 2024.

Builds on

41 of 46 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion18 Mar
  2. 2024V3D: Video Diffusion Models are Effective 3D Generators11 Mar
  3. 2023ReconFusion: 3D Reconstruction with Diffusion Priors5 Dec
  4. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model23 Oct
  5. 2023GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models12 Oct
  6. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  8. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models23 Feb
  9. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,418
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  10. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  11. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 837
  12. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
20 more
  1. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  2. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  3. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  4. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  5. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  6. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  7. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  8. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  9. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  10. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  11. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  12. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  13. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  14. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 124
  15. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  16. 2024IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generationcited by 84
  17. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  18. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  19. 2022AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Trainingcited by 31
  20. 2023Hardware Acceleration of Neural Graphicscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 52; 2026: 43.

106 papers.

Sort:

By area:

  1. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  2. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  3. 2024StreetCrafter: Street View Synthesis with Controllable Video Diffusion Modelscited by 49
  4. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  5. 2025EXP-Bench: Can AI Conduct AI Research Experiments?cited by 36
  6. 2025GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priorscited by 36
  7. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 34
  8. 2024FreeSim: Toward Free-viewpoint Camera Simulation in Driving Scenescited by 30
  9. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Priorcited by 30
  10. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputscited by 29
  11. 2025FlowR: Flowing from Sparse to Dense 3D Reconstructionscited by 28
  12. 2024Splatter-360: Generalizable 360circ Gaussian Splatting for Wide-baseline Panoramic Imagescited by 23
38 more
  1. 2025R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulationcited by 17
  2. 2025GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splattingcited by 17
  3. 2024SplatFormer: Point Transformer for Robust 3D Gaussian Splattingcited by 15
  4. 2024Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesiscited by 14
  5. 2025Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Modelcited by 13
  6. 20243DEnhancer: Consistent Multi-View Diffusion for 3D Enhancementcited by 12
  7. 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splattingcited by 12
  8. 2024Driving View Synthesis on Free-form Trajectories with Generative Priorcited by 11
  9. 2025G4Splat: Geometry-Guided Gaussian Splatting with Generative Priorcited by 10
  10. 2026One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Imagecited by 10
  11. 2026DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancercited by 10
  12. 2024Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priorscited by 8
  13. 2024Dust to Tower: Coarse-to-Fine Photo-Realistic Scene Reconstruction from Sparse Uncalibrated Imagescited by 8
  14. 2025WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Explorationcited by 7
  15. 2024Motion-Aware Animatable Gaussian Avatars Deblurringcited by 6
  16. 2025ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priorscited by 6
  17. 2026GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generatorcited by 6
  18. 2025TinySplat: Feedforward Approach for Generating Compact 3D Scene Representationcited by 5
  19. 2025DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splattingcited by 5
  20. 2025Low-Frequency First: Eliminating Floating Artifacts in 3D Gaussian Splattingcited by 5
  21. 2025LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Groundingcited by 5
  22. 2025CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesiscited by 5
  23. 2025From Orbit to Ground: Generative City Photogrammetry from Extreme Off-Nadir Satellite Imagescited by 5
  24. 2025Close-up-GS: Enhancing Close-Up View Synthesis in 3D Gaussian Splatting with Progressive Self-Trainingcited by 4
  25. 2025Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completioncited by 4
  26. 2025GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstructioncited by 4
  27. 2026GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Viewscited by 4
  28. 2025Uncertainty-Aware Diffusion Guided Refinement of 3D Scenescited by 3
  29. 2025SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priorscited by 3
  30. 2025VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Controlcited by 3
  31. 2025ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Viewscited by 3
  32. 2025ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priorscited by 3
  33. 2025FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillationcited by 3
  34. 2025SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit 3D Meshescited by 3
  35. 2025D2GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstructioncited by 3
  36. 2026GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesiscited by 3
  37. 2025Fillerbuster: Unified Generative Scene Completion Model for Casual Capturescited by 2
  38. 2025CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splattingcited by 2

50 most cited of 106 All 106 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors
  2. 2026Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion Models
  3. 2025Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views
  4. 2026GAPS: Generative Active Pseudo-view Selection for Sparse-View 3D Gaussian Splatting
  5. 2026Sparse View Distractor-Free Gaussian Splatting
  6. 2025Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis
  7. 20264DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors
  8. 2025OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting