mlsanityData to 14 Oct 2026

3D Gaussian Inpainting with Depth-Guided Cross-View Consistency

arXiv 2502.11801 ↗First posted 17 Feb 2025cs.CV cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

When performing 3D inpainting using novel-view rendering methods like Neural Radiance Field (NeRF) or 3D Gaussian Splatting (3DGS), how to achieve texture and geometry consistency across camera views has been a challenge. In this paper, we propose a framework of 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency (3DGIC) for cross-view consistent 3D inpainting. Guided by the rendered depth information from each training view, our 3DGIC exploits background pixels visible across different views for updating the inpainting mask, allowing us to refine the 3DGS for inpainting purposes.Through extensive experiments on benchmark datasets, we confirm that our 3DGIC outperforms current state-of-the-art 3D inpainting methods quantitatively and qualitatively.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 40 of its 49 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

40 of 49 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2023Segment Anythingcited by 8,234
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  10. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  11. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  12. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
28 more
  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  3. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  4. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  5. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  6. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  7. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  8. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  9. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  10. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  11. 2023LERF: Language Embedded Radiance Fieldscited by 543
  12. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  13. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  14. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
  15. 2022SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Modelcited by 278
  16. 2024A Survey on 3D Gaussian Splattingcited by 224
  17. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  18. 2022Removing Objects From Neural Radiance Fieldscited by 66
  19. 2023NeRFiller: Completing Scenes via Generative 3D Inpaintingcited by 62
  20. 2023Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Modelcited by 60
  21. 2024InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Priorcited by 56
  22. 2021EdgeFlow: Achieving Practical Interactive Segmentation with Edge-Guided Flowcited by 40
  23. 2023Reference-guided Controllable Inpainting of Neural Radiance Fieldscited by 40
  24. 2024GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removalcited by 39
  25. 2023OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fieldscited by 34
  26. 2024MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Priorcited by 24
  27. 2024RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpaintingcited by 21
  28. 2024Taming Latent Diffusion Model for Neural Radiance Field Inpaintingcited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 17.

24 papers.

Sort:

By area:

  1. 2025Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360deg Scenescited by 8
  2. 2026OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understandingcited by 5
  3. 2025High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic detailscited by 3
  4. 2025IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusioncited by 2
  5. 2026WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenescited by 2
  6. 2025DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removalcited by 1
  7. 2025DSG-World: Learning a 3D Gaussian World Model from Dual State Videoscited by 1
  8. 2025CoRe-GS: Coarse-to-Refined Gaussian Splatting with Semantic Object Focuscited by 1
  9. 2026GOR-IS: 3D Gaussian Object Removal in the Intrinsic Spacecited by 1
  10. 2026GASE: Gaussian Splatting-Based Automated System for Reconstructing Embodied-Simulation Environmentscited by 1
  11. 2026GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priorscited by 1
  12. 2025VEIGAR: View-consistent Explicit Inpainting and Geometry Alignment for 3D object Removalcited by 0
12 more
  1. 2026CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splattingcited by 0
  2. 2026Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setupscited by 0
  3. 2026Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignmentcited by 0
  4. 2026BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extractioncited by 0
  5. 2026Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenescited by 0
  6. 2026Lighting-Consistent Object Transfer Across Radiance Fieldscited by 0
  7. 2026CoIn: Comprehensive 2D-3D Inpainting with Gaussian Splatting Guidancecited by 0
  8. 2026Restore3D: Breathing Life into Broken Objects with Shape and Texture Restorationcited by 0
  9. 2026SSA-3DGS: Unsupervised Removal of Screen-Space Artifacts for 3D Gaussian Splattingcited by 0
  10. 2026Depth Estimators Are Implicit Neural Fields for 3D Scene Geometry Inpainting and Reconstructioncited by 0
  11. 2026GSComplete: Gaussian Splat Completion with 2D Diffusion Priorscited by 0
  12. 2026WINGS: Reference-Free Gaussian Splatting Inpainting with 3D-Native Generative Priorscited by 0