mlsanityData to 7 Oct 2026

FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling

arXiv 2104.08418 ↗First posted 17 Apr 2021cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object category models from collections of input images. In contrast to previous work, we are able to do this whilst simultaneously separating foreground objects from their varying backgrounds. We achieve this via a 2-component NeRF model, FiG-NeRF, that prefers explanation of the scene as a geometrically constant background and a deformable foreground that represents the object category. We show that this method can learn accurate 3D object category models using only photometric supervision and casually captured images of the objects. Additionally, our 2-part decomposition allows the model to perform accurate and crisp amodal segmentation. We quantitatively evaluate our method with view synthesis and image fidelity metrics, using synthetic, lab-captured, and in-the-wild data. Our results demonstrate convincing 3D object category modelling that exceed the performance of existing methods.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). Builds on 33 of its 49 references that are in the map. First posted on arXiv 17 Apr 2021.

Builds on

33 of 49 references.

References · 33

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 2017Mask R-CNNcited by 7,259
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  10. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  12. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
21 more
  1. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  2. 2017Neural 3D Mesh Renderercited by 437
  3. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  4. 2020State of the Art on Neural Renderingcited by 276
  5. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  6. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  7. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  8. 2017Optimizing the Latent Space of Generative Networkscited by 157
  9. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  10. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  11. 2015Semantic Amodal Segmentationcited by 102
  12. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  13. 2020STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Renderingcited by 76
  14. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  15. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  16. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  17. 2019SpineNet: Learning Scale-Permuted Backbone for Recognition and Localizationcited by 50
  18. 2017Learning 3D Object Categories by Looking Around Themcited by 26
  19. 2017SilNet : Single- and Multi-View Reconstruction by Learning from Silhouettescited by 24
  20. 2020Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivitycited by 15
  21. 2020GeLaTO: Generative Latent Textured Objectscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 14; 2024: 7; 2025: 2; 2026: 2.

47 papers.

Sort:

By area:

  1. 2021Neural Fields in Visual Computing and Beyondcited by 539
  2. 2021Advances in Neural Renderingcited by 365
  3. 2022Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representationscited by 195
  4. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  5. 2022NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editingcited by 141
  6. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  7. 2021LOLNeRF: Learn from One Lookcited by 84
  8. 2021Learning to Stylize Novel Viewscited by 76
  9. 2022AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fieldscited by 68
  10. 2021CoNeRF: Controllable Neural Radiance Fieldscited by 65
  11. 2023Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusioncited by 62
  12. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
35 more
  1. 2022AutoRF: Learning 3D Object Radiance Fields from Single View Observationscited by 59
  2. 2021NeuralDiff: Segmenting 3D objects that move in egocentric videoscited by 56
  3. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  4. 2022Self-supervised Neural Articulated Shape and Appearance Modelscited by 51
  5. 2023EPIC Fields: Marrying 3D Geometry and Video Understandingcited by 49
  6. 2023Reconstructing Animatable Categories from Videoscited by 46
  7. 2023NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mappingcited by 41
  8. 2022NeROIC: Neural Rendering of Objects from Online Image Collectionscited by 36
  9. 2024Mitigating Motion Blur in Neural Radiance Fields with Events and Framescited by 31
  10. 2022EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Pointscited by 30
  11. 2023MEGANE: Morphable Eyeglass and Avatar Networkcited by 24
  12. 2021CG-NeRF: Conditional Generative Neural Radiance Fieldscited by 18
  13. 2025DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splattingcited by 14
  14. 2023Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fieldscited by 10
  15. 2023CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Renderingcited by 10
  16. 2023Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wildcited by 9
  17. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  18. 2022Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objectscited by 8
  19. 2024SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destructioncited by 7
  20. 2022Physics vs. Learned Priors: Rethinking Camera and Algorithm Design for Task-Specific Imagingcited by 6
  21. 2022Neural Assets: Volumetric Object Capture and Rendering for Interactive Environmentscited by 6
  22. 2024Planar Gaussian Splattingcited by 6
  23. 2024ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decompositioncited by 5
  24. 2024CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesiscited by 4
  25. 2022Progressive Multi-scale Light Field Networkscited by 3
  26. 2022wildNeRF: Complete view synthesis of in-the-wild dynamic scenes captured using sparse monocular datacited by 3
  27. 2023Improving Neural Radiance Field using Near-Surface Sampling with Point Cloud Generationcited by 3
  28. 2023RefiNeRF: Modelling dynamic neural radiance fields with inconsistent or missing camera parameterscited by 2
  29. 2023Event-based Camera Tracker by nablat NeRFcited by 2
  30. 2023DORec: Decomposed Object Reconstruction and Segmentation Utilizing 2D Self-Supervised Featurescited by 1
  31. 2024Category-level Neural Field for Reconstruction of Partially Observed Objects in Indoor Environmentcited by 1
  32. 2026CEI-3D: Collaborative Explicit-Implicit 3D Reconstruction for Realistic and Fine-Grained Object Editingcited by 1
  33. 2026S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fieldscited by 1
  34. 2023BundleRecon: Ray Bundle-Based 3D Neural Reconstructioncited by 0
  35. 2025Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videoscited by 0