mlsanityData to 14 Oct 2026

Removing Objects From Neural Radiance Fields

arXiv 2212.11966 ↗First posted 22 Dec 2022cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Before sharing a NeRF, though, it might be desirable to remove personal information or unsightly objects. Such removal is not easily achieved with the current NeRF editing frameworks. We propose a framework to remove objects from a NeRF representation created from an RGB-D sequence. Our NeRF inpainting method leverages recent work in 2D image inpainting and is guided by a user-provided mask. Our algorithm is underpinned by a confidence based view selection procedure. It chooses which of the individual 2D inpainted images to use in the creation of the NeRF, so that the resulting inpainted NeRF is 3D consistent. We show that our method for NeRF editing is effective for synthesizing plausible inpaintings in a multi-view coherent manner. We validate our approach using a new and still-challenging dataset for the task of NeRF inpainting.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). Builds on 61 of its 85 references that are in the map. First posted on arXiv 22 Dec 2022.

Builds on

61 of 85 references.

References · 61

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2017Mask R-CNNcited by 7,277
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  8. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  9. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  10. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  11. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
38 more
  1. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  2. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  3. 2021Resolution-robust Large Mask Inpainting with Fourier Convolutionscited by 738
  4. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  5. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  6. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  7. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  8. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  9. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  10. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  11. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  12. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  13. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  14. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  15. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  16. 2021Urban Radiance Fieldscited by 263
  17. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  18. 2021Editing Conditional Radiance Fieldscited by 222
  19. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 217
  20. 20203D Photography using Context-aware Layered Depth Inpaintingcited by 206
  21. 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 182
  22. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
  23. 2020Learning Joint Spatial-Temporal Transformations for Video Inpaintingcited by 163
  24. 2019Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesiscited by 161
  25. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  26. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  27. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  28. 2021Pathdreamer: A World Model for Indoor Navigationcited by 118
  29. 2021LENS: Localization enhanced by NeRF synthesiscited by 117
  30. 2019Deep Flow-Guided Video Inpaintingcited by 116
  31. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 113
  32. 2020Flow-edge Guided Video Completioncited by 104
  33. 2019Learning to Infer Implicit Surfaces without 3D Supervisioncited by 103
  34. 2019Learning Pyramid-Context Encoder Network for High-Quality Image Inpaintingcited by 94
  35. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  36. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  37. 2022Object-Compositional Neural Implicit Surfacescited by 74
  38. 2019HoloGAN: Unsupervised learning of 3D representations from natural imagescited by 59

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 13; 2024: 26; 2025: 20; 2026: 7.

66 papers.

Sort:

By area:

  1. 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 94
  2. 2023NeRFiller: Completing Scenes via Generative 3D Inpaintingcited by 62
  3. 2024InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Priorcited by 56
  4. 2023PIE-NeRF: Physics-based Interactive Elastodynamics with NeRFcited by 51
  5. 2023Watch Your Steps: Local Image and Scene Editing by Text Instructionscited by 50
  6. 2023PERF: Panoramic Neural Radiance Field from a Single Panoramacited by 45
  7. 2024GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removalcited by 39
  8. 2023SHAP-EDITOR: Instruction-guided Latent 3D Editing in Secondscited by 37
  9. 2023OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fieldscited by 34
  10. 2024MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editingcited by 30
  11. 2023Point'n Move: Interactive Scene Object Manipulation on Gaussian Splatting Radiance Fieldscited by 27
  12. 2024NeRF-HuGS: Improved Neural Radiance Fields in Non-static Scenes Using Heuristics-Guided Segmentationcited by 25
38 more
  1. 2024MVIP-NeRF: Multi-view 3D Inpainting on NeRF Scenes via Diffusion Priorcited by 24
  2. 20253D Gaussian Inpainting with Depth-Guided Cross-View Consistencycited by 24
  3. 2024RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpaintingcited by 21
  4. 2025AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpaintingcited by 21
  5. 2024Taming Latent Diffusion Model for Neural Radiance Field Inpaintingcited by 20
  6. 2023RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Modelscited by 19
  7. 2024Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splattingcited by 18
  8. 2023InNeRF360: Text-Guided 3D-Consistent Object Inpainting on 360-degree Neural Radiance Fieldscited by 16
  9. 2023Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusioncited by 13
  10. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  11. 2024InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenescited by 11
  12. 2025IMFine: 3D Inpainting via Geometry-guided Multi-view Refinementcited by 10
  13. 2025InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Modelcited by 10
  14. 2023Clutter Detection and Removal in 3D Scenes with View-Consistent Inpaintingcited by 9
  15. 2023Language-driven Object Fusion into Neural Radiance Fields with Pose-Conditioned Dataset Updatescited by 9
  16. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  17. 2024DerainNeRF: 3D Scene Estimation with Adhesive Waterdrop Removalcited by 9
  18. 2025Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360deg Scenescited by 8
  19. 2024ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fieldscited by 7
  20. 2024IE-NeRF: Inpainting Enhanced Neural Radiance Fields in the Wildcited by 6
  21. 2025Geometry-Aware Diffusion Models for Multiview Scene Inpaintingcited by 6
  22. 2024OmniLocalRF: Omnidirectional Local Radiance Fields from Dynamic Videoscited by 5
  23. 2026OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D Scene Understandingcited by 5
  24. 2024DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Imagescited by 4
  25. 2024NeRF-Insert: 3D Local Editing with Multimodal Control Signalscited by 4
  26. 20243D StreetUnveiler with Semantic-aware 2DGS -- a simple baselinecited by 4
  27. 2025Affine-Equivariant Kernel Space Encoding for NeRF Editingcited by 4
  28. 2026PhaSR: Generalized Image Shadow Removal with Physically Aligned Priorscited by 4
  29. 2024Fast Sparse View Guided NeRF Update for Object Reconfigurationscited by 3
  30. 2024SCINeRF: Neural Radiance Fields from a Snapshot Compressive Imagecited by 3
  31. 2025High-fidelity 3D Gaussian Inpainting: preserving multi-view consistency and photorealistic detailscited by 3
  32. 2025Perspective-aware 3D Gaussian Inpainting with Multi-view Consistencycited by 3
  33. 2024InfoNorm: Mutual Information Shaping of Normals for Sparse-View Reconstructioncited by 2
  34. 2025HOMER: Homography-Based Efficient Multi-view 3D Object Removalcited by 2
  35. 2025Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splattingcited by 2
  36. 2025HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesiscited by 2
  37. 2026IRIS: Intersection-aware Ray-based Implicit Editable Scenescited by 2
  38. 2023FusedRF: Fusing Multiple Radiance Fieldscited by 1

50 most cited of 66 All 66 (JSON)