mlsanityData to 7 Oct 2026

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering

arXiv 2109.01847 ↗First posted 4 Sep 2021cs.CVcited by 228

Not on the map. Why?

Abstract (arXiv)

Implicit neural rendering techniques have shown promising results for novel view synthesis. However, existing methods usually encode the entire scene as a whole, which is generally not aware of the object identity and limits the ability to the high-level editing tasks such as moving or adding furniture. In this paper, we present a novel neural scene rendering system, which learns an object-compositional neural radiance field and produces realistic rendering with editing capability for a clustered and real-world scene. Specifically, we design a novel two-pathway architecture, in which the scene branch encodes the scene geometry and appearance, and the object branch encodes each standalone object conditioned on learnable object activation codes. To survive the training in heavily cluttered scenes, we propose a scene-guided training strategy to solve the 3D space ambiguity in the occluded regions and learn sharp boundaries for each object. Extensive experiments demonstrate that our system not only achieves competitive performance for static scene novel-view synthesis, but also produces realistic rendering for object-level editing.

Key facts. Cited by 228 papers in the map (data through 7 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 4 Sep 2021.

Builds on

17 of 37 references.

References · 17

  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  2. 2020Neural Sparse Voxel Fieldscited by 959
  3. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  4. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  5. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  6. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  7. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  8. 2019Neural Point-Based Graphicscited by 326
  9. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  10. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  11. 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 144
  12. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
5 more
  1. 2019Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesiscited by 104
  2. 2020Object-Centric Neural Scene Renderingcited by 90
  3. 2019Rendering Synthetic Objects into Legacy Photographscited by 72
  4. 2019Revealing Scenes by Inverting Structure from Motion Reconstructionscited by 66
  5. 2019Neural Point Cloud Rendering via Multi-Plane Projectioncited by 60

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 52; 2023: 96; 2024: 46; 2025: 17; 2026: 7.

228 papers.

Sort:

By area:

  1. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  2. 2021Neural Fields in Visual Computing and Beyondcited by 539
  3. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 387
  4. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  5. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  6. 2021Urban Radiance Fieldscited by 263
  7. 2022NeuMan: Neural Human Radiance Field from a Single Videocited by 244
  8. 2022Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representationcited by 243
  9. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  10. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  11. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  12. 2022NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fieldscited by 151
38 more
  1. 2023SUDS: Scalable Urban Dynamic Scenescited by 151
  2. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  3. 2022SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fieldscited by 144
  4. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 141
  5. 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splattingcited by 141
  6. 2021NeRFReN: Neural Radiance Fields with Reflectionscited by 121
  7. 2022Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generationcited by 119
  8. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 113
  9. 2023Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinementcited by 106
  10. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  11. 2023SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Fieldcited by 93
  12. 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
  13. 2022EventNeRF: Neural Radiance Fields from a Single Colour Event Cameracited by 92
  14. 2024DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editingcited by 92
  15. 2022BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fieldscited by 80
  16. 2022Deforming Radiance Fields with Cagescited by 78
  17. 2023Neural Residual Radiance Fields for Streamably Free-Viewpoint Videoscited by 77
  18. 2023Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenescited by 75
  19. 2023FocalDreamer: Text-driven 3D Editing via Focal-fusion Assemblycited by 75
  20. 2022Object-Compositional Neural Implicit Surfacescited by 74
  21. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  22. 2022DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Imagescited by 69
  23. 2022AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fieldscited by 68
  24. 2024ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fieldscited by 68
  25. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  26. 2022Removing Objects From Neural Radiance Fieldscited by 66
  27. 2021CoNeRF: Controllable Neural Radiance Fieldscited by 65
  28. 2024Advances in 3D Generation: A Surveycited by 62
  29. 2022Neural Volumetric Object Selectioncited by 61
  30. 2022DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesiscited by 61
  31. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  32. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  33. 20223DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Modelscited by 57
  34. 2023CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layoutcited by 57
  35. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  36. 2023PIE-NeRF: Physics-based Interactive Elastodynamics with NeRFcited by 51
  37. 2023Watch Your Steps: Local Image and Scene Editing by Text Instructionscited by 50
  38. 2023EPIC Fields: Marrying 3D Geometry and Video Understandingcited by 49

50 most cited of 228 All 228 (JSON)