mlsanityData to 7 Oct 2026

3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement

arXiv 2412.18565 ↗First posted 24 Dec 2024cs.CVcited by 12

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

Abstract (arXiv)

Despite advances in neural rendering, due to the scarcity of high-quality 3D datasets and the inherent limitations of multi-view diffusion models, view synthesis and 3D model generation are restricted to low resolutions with suboptimal multi-view consistency. In this study, we present a novel 3D enhancement pipeline, dubbed 3DEnhancer, which employs a multi-view latent diffusion model to enhance coarse 3D inputs while preserving multi-view consistency. Our method includes a pose-aware encoder and a diffusion-based denoiser to refine low-quality multi-view images, along with data augmentation and a multi-view attention module with epipolar aggregation to maintain consistent, high-quality 3D outputs across views. Unlike existing video-based approaches, our model supports seamless multi-view enhancement with improved coherence across diverse viewing angles. Extensive evaluations show that 3DEnhancer significantly outperforms existing methods, boosting both multi-view enhancement and per-instance 3D optimization tasks.

Key facts. Cited by 12 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 87 of its 99 references that are in the map. First posted on arXiv 24 Dec 2024.

Builds on

87 of 99 references.

Closest ancestors · 19

Same direction, newest first

  1. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors21 Oct
  2. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets30 May
  3. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image30 May
  4. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Models16 May
  5. 20243DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors4 Mar
  6. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion11 Dec
  7. 2023ReconFusion: 3D Reconstruction with Diffusion Priors5 Dec
  8. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation2 Dec
  9. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D28 Nov
  10. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model23 Oct
  11. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusion23 Oct
  12. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
7 more
  1. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  2. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  3. 2023Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction24 May
  4. 2023Consistent View Synthesis with Pose-Guided Diffusion Models30 Mar
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  6. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models26 Jan
  7. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 68

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  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. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  8. 2022Scalable Diffusion Models with Transformerscited by 5,931
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  11. 2017Neural Discrete Representation Learningcited by 4,650
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
38 more
  1. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  2. 2016Improved Techniques for Training GANscited by 2,938
  3. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  4. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  8. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  9. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  10. 2020Pre-Trained Image Processing Transformercited by 891
  11. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  12. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  13. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  14. 2021Score-based Generative Modeling in Latent Spacecited by 634
  15. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  16. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  17. 2019EDVR: Video Restoration with Enhanced Deformable Convolutional Networkscited by 492
  18. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  19. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
  20. 2023TokenFlow: Consistent Diffusion Features for Consistent Video Editingcited by 440
  21. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  22. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  23. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 379
  24. 2021Advances in Neural Renderingcited by 365
  25. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  26. 2021BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignmentcited by 340
  27. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  28. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 326
  29. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  30. 2020BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyondcited by 303
  31. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  32. 2022Towards Robust Blind Face Restoration with Codebook Lookup Transformercited by 230
  33. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  34. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  35. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  36. 2022Recurrent Video Restoration Transformer with Guided Deformable Attentioncited by 168
  37. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  38. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 6.

12 papers.

  1. 2025CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editingcited by 5
  2. 2026SyncFix: Fixing 3D Reconstructions via Multi-View Synchronizationcited by 4
  3. 2025Collaborative Multi-Modal Coding for High-Quality 3D Generationcited by 3
  4. 2025Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Viewscited by 3
  5. 2025PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Modelscited by 2
  6. 2026GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priorscited by 1
  7. 2025SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuningcited by 0
  8. 2025MemeCMD: An Automatically Generated Chinese Multi-turn Dialogue Dataset with Contextually Retrieved Memescited by 0
  9. 2026Restore3D: Breathing Life into Broken Objects with Shape and Texture Restorationcited by 0
  10. 2026RealSkin: Spatio-Spectral Partial Neural Adjoint Maps for Image-to-3D Attribute Transfercited by 0
  11. 2026TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restorationcited by 0
  12. 2026CasDeblurGS: Cascaded 2D-to-3D Multi-View Consistency for 3D Gaussian Splatting from Two Blurry Imagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 20243D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation
  2. 2024Envision3D: One Image to 3D with Anchor Views Interpolation
  3. 2025NOVA3D: Normal Aligned Video Diffusion Model for Single Image to 3D Generation
  4. 2024Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion
  5. 2024Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data
  6. 2025Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
  7. 2024Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models
  8. 2024Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models