mlsanityData to 14 Oct 2026

Interactive Segmentation of Radiance Fields

arXiv 2212.13545 ↗First posted 27 Dec 2022cs.CVcited by 60

Not on the map. Why?

Abstract (arXiv)

Radiance Fields (RF) are popular to represent casually-captured scenes for new view synthesis and several applications beyond it. Mixed reality on personal spaces needs understanding and manipulating scenes represented as RFs, with semantic segmentation of objects as an important step. Prior segmentation efforts show promise but don't scale to complex objects with diverse appearance. We present the ISRF method to interactively segment objects with fine structure and appearance. Nearest neighbor feature matching using distilled semantic features identifies high-confidence seed regions. Bilateral search in a joint spatio-semantic space grows the region to recover accurate segmentation. We show state-of-the-art results of segmenting objects from RFs and compositing them to another scene, changing appearance, etc., and an interactive segmentation tool that others can use. Project Page: https://rahul-goel.github.io/isrf/

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Builds on 53 of its 67 references that are in the map. First posted on arXiv 27 Dec 2022.

Builds on

53 of 67 references.

References · 53

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  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. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  9. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  10. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  11. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
38 more
  1. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  2. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  3. 2022Language-driven Semantic Segmentationcited by 717
  4. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  5. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  6. 2021Neural Fields in Visual Computing and Beyondcited by 540
  7. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  8. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 471
  9. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  10. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  11. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
  12. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  13. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  14. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  15. 2021Advances in Neural Renderingcited by 365
  16. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 344
  17. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  18. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  19. 2021BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Renderingcited by 229
  20. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 214
  21. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
  22. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 196
  23. 2022Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentationcited by 152
  24. 2022ARF: Artistic Radiance Fieldscited by 147
  25. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 142
  26. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  27. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 137
  28. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  29. 2022Reconstructing Personalized Semantic Facial NeRF Models From Monocular Videocited by 128
  30. 2020f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentationcited by 117
  31. 2022IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Imagescited by 111
  32. 2022NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fieldscited by 86
  33. 2022Deforming Radiance Fields with Cagescited by 78
  34. 2022Loc-NeRF: Monte Carlo Localization using Neural Radiance Fieldscited by 69
  35. 2022Neural Volumetric Object Selectioncited by 61
  36. 2022Improved Direct Voxel Grid Optimization for Radiance Fields Reconstructioncited by 61
  37. 2022CLA-NeRF: Category-Level Articulated Neural Radiance Fieldcited by 56
  38. 2022PANDORA: Polarization-Aided Neural Decomposition Of Radiancecited by 52

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 15; 2024: 22; 2025: 16; 2026: 7.

60 papers.

Sort:

  1. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  2. 2023Segment Any 3D Gaussianscited by 161
  3. 2023Weakly Supervised 3D Open-vocabulary Segmentationcited by 135
  4. 2023OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learningcited by 75
  5. 2023SATR: Zero-Shot Semantic Segmentation of 3D Shapescited by 62
  6. 2023Segment Anything in 3D with Radiance Fieldscited by 62
  7. 2024FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimallycited by 58
  8. 2024LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenescited by 37
  9. 2023OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fieldscited by 34
  10. 2024N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fieldscited by 34
  11. 2023Zero-Shot 3D Shape Correspondencecited by 33
  12. 2024SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decompositioncited by 30
38 more
  1. 2024GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splattingcited by 25
  2. 2025ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splattingcited by 25
  3. 2023Interactive Segment Anything NeRF with Feature Imitationcited by 24
  4. 2024MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesiscited by 22
  5. 2023SANeRF-HQ: Segment Anything for NeRF in High Qualitycited by 20
  6. 2024Segment Any 4D Gaussianscited by 20
  7. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  8. 2024SLGaussian: Fast Language Gaussian Splatting in Sparse Viewscited by 18
  9. 2024PLGS: Robust Panoptic Lifting with 3D Gaussian Splattingcited by 17
  10. 2024Occam's LGS: An Efficient Approach for Language Gaussian Splattingcited by 16
  11. 2025Tackling View-Dependent Semantics in 3D Language Gaussian Splattingcited by 16
  12. 2024Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3Dcited by 15
  13. 2024ChatCam: Empowering Camera Control through Conversational AIcited by 15
  14. 2023NTO3D: Neural Target Object 3D Reconstruction with Segment Anythingcited by 14
  15. 2025Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracingcited by 13
  16. 20232D-Guided 3D Gaussian Segmentationcited by 12
  17. 2024Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interactioncited by 12
  18. 2025iSegMan: Interactive Segment-and-Manipulate 3D Gaussianscited by 11
  19. 2024SAMa: Material-aware 3D Selection and Segmentationcited by 10
  20. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  21. 2025PE3R: Perception-Efficient 3D Reconstructioncited by 9
  22. 2023DAE-Net: Deforming Auto-Encoder for fine-grained shape co-segmentationcited by 7
  23. 2024Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Samplingcited by 7
  24. 2025Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Fieldcited by 7
  25. 2024LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Rendering and Controlcited by 6
  26. 2025WildSeg3D: Segment Any 3D Objects in the Wild from 2D Imagescited by 6
  27. 20234D-Editor: Interactive Object-level Editing in Dynamic Neural Radiance Fields via Semantic Distillationcited by 5
  28. 2025EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splattingcited by 4
  29. 2024Fast Sparse View Guided NeRF Update for Object Reconfigurationscited by 3
  30. 2024Scale Disparity of Instances in Interactive Point Cloud Segmentationcited by 3
  31. 2025FMLGS: Fast Multilevel Language Embedded Gaussians for Part-level Interactive Agentscited by 3
  32. 2025SAGOnline: Segment Any Gaussians Onlinecited by 3
  33. 2023FusedRF: Fusing Multiple Radiance Fieldscited by 1
  34. 2024GSN: Generalisable Segmentation in Neural Radiance Fieldcited by 1
  35. 2024Computer vision tasks for intelligent aerospace missions: An overviewcited by 1
  36. 2025Binary-Gaussian: Compact and Progressive Representation for 3D Gaussian Segmentationcited by 1
  37. 2025Next Best View Selections for Semantic and Dynamic 3D Gaussian Splattingcited by 1
  38. 2026Semantic Foam: Unifying Spatial and Semantic Scene Decompositioncited by 1

50 most cited of 60 All 60 (JSON)