mlsanityData to 7 Oct 2026

Convolutional Occupancy Networks

arXiv 2003.04618 ↗First posted 10 Mar 2020cs.CVcited by 760

Not on the map. Why?

Cited by 44 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not scale to more complicated or large-scale scenes. The key limiting factor of implicit methods is their simple fully-connected network architecture which does not allow for integrating local information in the observations or incorporating inductive biases such as translational equivariance. In this paper, we propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We investigate the effectiveness of the proposed representation by reconstructing complex geometry from noisy point clouds and low-resolution voxel representations. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.

Key facts. Cited by 760 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 125; 2022: 175; 2023: 208; 2024: 148; 2025: 75; 2026: 29.

760 papers.

Sort:

By area:

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  3. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  4. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  5. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  6. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  7. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  8. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  10. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  11. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  12. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
38 more
  1. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  2. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  3. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  4. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  5. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  6. 2021Neural Fields in Visual Computing and Beyondcited by 539
  7. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  8. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  9. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  10. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  11. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  12. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  13. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  14. 2021Dynamic View Synthesis from Dynamic Monocular Videocited by 420
  15. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  16. 2021Advances in Neural Renderingcited by 365
  17. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  18. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  19. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  20. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  21. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  22. 2021Neural RGB-D Surface Reconstructioncited by 312
  23. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  24. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  25. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  26. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  27. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  28. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  29. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  30. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  31. 2021NeRV: Neural Representations for Videoscited by 255
  32. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  33. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  34. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  35. 2021Editing Conditional Radiance Fieldscited by 222
  36. 2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
  37. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  38. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211

50 most cited of 760 All 760 (JSON)