mlsanityData to 14 Oct 2026

Occupancy Networks: Learning 3D Reconstruction in Function Space

arXiv 1812.03828 ↗First posted 10 Dec 2018cs.CVcited by 2,041

Not on the map. Why?

Cited by 103 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representation which is both computationally and memory efficient yet allows for representing high-resolution geometry of arbitrary topology. Many of the state-of-the-art learning-based 3D reconstruction approaches can hence only represent very coarse 3D geometry or are limited to a restricted domain. In this paper, we propose Occupancy Networks, a new representation for learning-based 3D reconstruction methods. Occupancy networks implicitly represent the 3D surface as the continuous decision boundary of a deep neural network classifier. In contrast to existing approaches, our representation encodes a description of the 3D output at infinite resolution without excessive memory footprint. We validate that our representation can efficiently encode 3D structure and can be inferred from various kinds of input. Our experiments demonstrate competitive results, both qualitatively and quantitatively, for the challenging tasks of 3D reconstruction from single images, noisy point clouds and coarse discrete voxel grids. We believe that occupancy networks will become a useful tool in a wide variety of learning-based 3D tasks.

Key facts. Cited by 2,041 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 325; 2022: 423; 2023: 516; 2024: 399; 2025: 230; 2026: 148.

2,041 papers.

Sort:

By area:

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  3. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  4. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  5. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  8. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  9. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  12. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
38 more
  1. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  2. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  3. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  4. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  5. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  6. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  7. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  9. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  10. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  11. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  12. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  13. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  14. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  15. 2021Neural Fields in Visual Computing and Beyondcited by 540
  16. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  17. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  18. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  19. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  20. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  21. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 460
  22. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  23. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 455
  24. 2021Implicit Behavioral Cloningcited by 452
  25. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  26. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 433
  27. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  28. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  29. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
  30. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 409
  31. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  32. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  33. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
  34. 2021Advances in Neural Renderingcited by 365
  35. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  36. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  37. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  38. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335

50 most cited of 2,041 All 2,041 (JSON)