mlsanityData to 7 Oct 2026

ONeRF: Unsupervised 3D Object Segmentation from Multiple Views

arXiv 2211.12038 ↗First posted 22 Nov 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations. The segmented 3D objects are represented using separate Neural Radiance Fields (NeRFs) which allow for various 3D scene editing and novel view rendering. At the core of our method is an unsupervised approach using the iterative Expectation-Maximization algorithm, which effectively aggregates 2D visual features and the corresponding 3D cues from multi-views for joint 3D object segmentation and reconstruction. Unlike existing approaches that can only handle simple objects, our method produces segmented full 3D NeRFs of individual objects with complex shapes, topologies and appearance. The segmented ONeRfs enable a range of 3D scene editing, such as object transformation, insertion and deletion.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 56 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

42 of 56 references.

References · 42

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  8. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  9. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  10. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  11. 2020Object-Centric Learning with Slot Attentioncited by 865
  12. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
30 more
  1. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  2. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  3. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  4. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  5. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  6. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  7. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  8. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  9. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  10. 2021AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesiscited by 339
  11. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  12. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  13. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  14. 2021Editing Conditional Radiance Fieldscited by 222
  15. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  16. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  17. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  18. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  19. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  20. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  21. 2016Learning-Based View Synthesis for Light Field Camerascited by 145
  22. 2021Unsupervised Discovery of Object Radiance Fieldscited by 100
  23. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  24. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  25. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  26. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  27. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  28. 2020Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clusteringcited by 61
  29. 2021NeuralDiff: Segmenting 3D objects that move in egocentric videoscited by 56
  30. 2019Point Cloud Instance Segmentation using Probabilistic Embeddingscited by 52

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 1.

6 papers.

  1. 2023Weakly Supervised 3D Open-vocabulary Segmentationcited by 133
  2. 2023Interactive Segment Anything NeRF with Feature Imitationcited by 24
  3. 2024NeRFs in Robotics: A Surveycited by 16
  4. 2024Unsupervised Discovery of Object-Centric Neural Fieldscited by 12
  5. 2024Fast Sparse View Guided NeRF Update for Object Reconfigurationscited by 3
  6. 2025UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fieldscited by 2